Tokushima University / Educator and Researcher Directory --- Karungaru, Stephen Githinji

Personal Web Page

http://www-b1.is.tokushima-u.ac.jp/~karunga/

https://researchmap.jp/read0119888 (researchmap)

Field of Study

○	Information Technology
○	Information Technology

Subject of Study

○	Automatic Face Detection and Recognition (Face Detection, Recognition, Neural Networks, Genetic Algorithms)
○	Abandoned object Detection and Recognition, Online character recognition for mobile devices (Face Detection, Recognition, Neural Networks, Genetic Algorithms, Character Recognition, Aerial image processing)

Book / Paper

Book:

1.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Character Recognition from Virtual Scenes and Vehicle License Plates using Genetic Algorithms and Neural Networks, InTech Inc, Oct. 2012. (Link to Publication Site) ● Publication site (DOI): 10.5772/2575 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.5772/2575 (DOI: 10.5772/2575)
2.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Neural Networks and 3D Edge genetic Template Matching for Real Time Face Detection and Recognition, Chapter 9, Idea Group Inc, Oct. 2006.

Academic Paper (Judged Full Paper):

1.	Sonom-Ochir Ulziibayar, Stephen Githinji Karungaru and Kenji Terada : Domain Adaptation for Drivers Gaze Mapping for Different Drivers and New Environments, International Journal of Advances in Intelligent Informatics,, Vol.10, No.02, 2442-6571, 2024. (Keyword) pattern recognition / image processing / measurement / deep learning / ITS
2.	Haoran Ji, Stephen Githinji Karungaru and Kenji Terada : AI Fitness Coach at Home using Image Processing, International Journal of Human Movement and Sports Sciences, Vol.11, No.4, 1-8, 2023. (Summary) The COVID-19 pandemic has forced manypeople to exercise at home, leading to a surge in demandfor effective and safe workout programs. However,traditional online exercise videos are often lacking inreal-time feedback, which can compromise exercise safetyand effectiveness. To address this issue, an AI-basedfitness monitoring system, the AI Fitness Coach, hasbeen developed to provide users with real-time guidanceand advice to improve the quality of at-home exerciseand reduce the risk of injury. The AI Fitness Coachsystem utilizes three key units - a pose recognition unit,a fitness movement analysis unit, and a feedback unit - tomonitor and guide the users exercise routine in real-time.By processing images from a fixed camera, the systemanalyzes the users movements and provides feedbackthrough either video or voice. This technology has beenfound to be highly effective in improving exercise qualityat home, leading to enhanced performance and reducedrisk of injury. This article provides an introduction tothe AI Fitness Coach and explores its effectiveness andlimitations. The methodology and technology presentedin this study can offer new ideas and references for the development of future fitness monitoring systems. Despitethe systems impressive results, it has some limitations,such as its requirements for user posture and movement,which make it unsuitable for certain populations. Futureresearch can focus on improving the systems accuracyand applicability. In summary, the AI Fitness Coach isa promising technology that provides a safer and moreeffective way for people to exercise at home. It notonly meets the growing demand for personalized fitnessguidance during the pandemic but also offers new insightsfor the development of fitness monitoring systems. Byenhancing the quality and safety of at-home exercise,the AI Fitness Coach has the potential to revolutionizethe way people exercise and maintain their health in thefuture (Keyword) Pose Recognition / Fitness / Movement Analysis
3.	Ni Hongjun, Shi Zhiwei, Stephen Githinji Karungaru, Lv Shuaishuai and Li Xiaoyuan : Classification of Typical Pests and Diseases of Rice Based on the ECA Attention Mechanism, Agriculture, Vol.13, No.1066, 1-15, 2023. (Summary) Rice, a staple food crop worldwide, is pivotal in agricultural productivity and publichealth. Automatic classification of typical rice pests and diseases is crucial for optimizing rice yieldand quality in practical production. However, infrequent occurrences of specific pests and diseaseslead to uneven dataset samples and similar early-stage symptoms, posing challenges for effectiveidentification methods. In this study, we employ four image enhancement techniquesflipping,modifying saturation, modifying contrast, and adding blurto balance dataset samples throughoutthe classification process. Simultaneously, we enhance the basic RepVGG model by incorporatingthe ECA attention mechanism within the Block and after the Head, resulting in the proposal of anew classification model, RepVGG_ECA. The model successfully classifies six categories: five types oftypical pests and diseases, along with healthy rice plants, achieving a classification accuracy of 97.06%,outperforming ResNet34, ResNeXt50, Shufflenet V2, and the basic RepVGG by 1.85%, 1.18%, 3.39%, and1.09%, respectively. Furthermore, the ablation study demonstrates that optimal classification resultsare attained by integrating the ECA attention mechanism after the Head and within the Block ofRepVGG. As a result, the classification method presented in this study provides a valuable referencefor identifying typical rice pests and diseases (Keyword) Rice Classificaton / Pests and Disease classification / ECA / Attention mechanism / Deep Learning (Tokushima University Institutional Repository) ● Metadata: 118869 (Link to Publication Site) ● Publication site (DOI): 10.3390/agriculture13051066 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.3390/agriculture13051066 (Tokushima University Institutional Repository: 118869, DOI: 10.3390/agriculture13051066)
4.	Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada and Naka Gotoda : Double-sided design for reinforcing private training of basketball with an advanced imagery opponent, International Journal of Learning Technologies and Learning Environments, Vol.6, No.1, 18pgs, 2023. (Keyword) Mental imagery training / basketball / one-to-one / visualized opponent (Link to Publication Site) ● Publication site (DOI): 10.52731/ijltle.v6.i1.718 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390295956282570112 ● Search Scopus @ Elsevier (DOI): 10.52731/ijltle.v6.i1.718 (DOI: 10.52731/ijltle.v6.i1.718, CiNii: 1390295956282570112)
5.	Stephen Githinji Karungaru, Kenji Terada and Tsuji Ryosuke : Driving Assistance: Pedestrians and Bicycles Accident Risk Estimation using Onboard Front Camera, International Journal of Intelligent Transportation Systems Research, 1-10, 2022. (Keyword) pattern recognition / image processing / deep learning / ITS (Tokushima University Institutional Repository) ● Metadata: 118382 (Link to Publication Site) ● Publication site (DOI): 10.1007/s13177-022-00324-2 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85138069485 (Tokushima University Institutional Repository: 118382, DOI: 10.1007/s13177-022-00324-2, Elsevier: Scopus)
6.	Sonom-Ochir Ulziibayar, Stephen Githinji Karungaru and Kenji Terada : DETECTION OF DRIVER'S VISUAL DISTRACTION USING DUAL CAMERAS, International Journal of Innovative Computing, Information and Control, Vol.18, No.05, 1445-1461, 2022. (Keyword) pattern recognition / image processing / measurement / deep learning / ITS (Tokushima University Institutional Repository) ● Metadata: 118053 (Link to Publication Site) ● Publication site (DOI): 10.24507/ijicic.18.05.1445 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390293180217667328 ● Search Scopus @ Elsevier (DOI): 10.24507/ijicic.18.05.1445 (Tokushima University Institutional Repository: 118053, DOI: 10.24507/ijicic.18.05.1445, CiNii: 1390293180217667328)
7.	Robert Nsinga, Stephen Githinji Karungaru and Kenji Terada : Auto-Differentiated Fixed Point Notation on Low-powered Hardware Acceleration, Journal of Signal Processing, Vol.26, No.5, 131-140, 2022. (Keyword) Embedded Systems / IEEE 754-2008 floating-point / Digital signal processor / Q format notation (Tokushima University Institutional Repository) ● Metadata: 118049 (Link to Publication Site) ● Publication site (DOI): 10.2299/jsp.26.131 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390011793672543360 ● Search Scopus @ Elsevier (DOI): 10.2299/jsp.26.131 (Tokushima University Institutional Repository: 118049, DOI: 10.2299/jsp.26.131, CiNii: 1390011793672543360)
8.	Abdelrahman Abdelkader Maher Harras, Akinori Tsuji, Stephen Githinji Karungaru and Kenji Terada : Enhanced Vehicle Classification Using Transfer Learning and a Novel Duplication-based Data Augmentation Technique, International Journal of Innovative Computing, Information and Control, Vol.17, No.6, 2201-2016, 2021. (Keyword) pattern recognition / image processing / measurement / deep learning / ITS (Link to Publication Site) ● Publication site (DOI): 10.24507/ijicic.17.06.2201 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.24507/ijicic.17.06.2201 (DOI: 10.24507/ijicic.17.06.2201)
9.	Stephen Githinji Karungaru, Dongyang Lyu and Kenji Terada : Vehicle Detection and Type Classification based on CNN-SVM, International Journal of Machine Learning and Computing, Vol.11, No.4, 304-310, 2021. (Summary) 本稿では，改良されたAlexNetを用いた実道路環境における車両の検出と車種分類を提案する．この手法は物体認識モデルであるAlexNetのサイズを小さくし，分類速度を高速化した上で， SVMによる特徴量の正規化とSpatial Pyramid Poolingによる画像歪み補正により，車両検出や種別分類の性能を向上させることができた．本手法の有効性を検証する実験によって，高い車両検出と種類分類精度を得られることを示した． (Keyword) Vehicle Detection / CNN-SVM / AlexNet / 空間ピラミッドプーリング (Tokushima University Institutional Repository) ● Metadata: 115186 (Link to Publication Site) ● Publication site (DOI): 10.18178/ijmlc.2021.11.4.1052 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.18178/ijmlc.2021.11.4.1052 (Tokushima University Institutional Repository: 115186, DOI: 10.18178/ijmlc.2021.11.4.1052)
10.	Jargalsaikhan Orgil, Stephen Githinji Karungaru, Kenji Terada and Shagdar Ganbold : Multimodal Emotion Recognition using Non-Inertial Loss function, Journal of Signal Processing, Vol.25, No.2, 73-85, 2021. (Summary) Automatic understanding of human emotion in a wild setting using audiovisual signals is extremely challenging. Latent continuous dimensions can be used to accomplish the analysis of human emotional states, behaviors, and reactions displayed in real-world settings. Moreover, Valence and Arousal combinations constitute well-known and effective representations of emotions.In this paper, a new Non-inertial loss function is proposed to train emotion recognition deep learning models. It is evaluated in wild settings using four types of candidate networks with different pipelines and sequence lengths. It is then compared to the Concordance Correlation Coefficient (CCC) and Mean Squared Error (MSE) losses commonly used for training. To prove its effectiveness on efficiency and stability in continuous or non-continuous input data, experiments were performed using the Aff-Wild dataset. Encouraging results were obtained. (Keyword) image processing / pattern recognition / emotion recognition / human sensing (Tokushima University Institutional Repository) ● Metadata: 116447 (Link to Publication Site) ● Publication site (DOI): 10.2299/jsp.25.73 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390850247496582016 ● Search Scopus @ Elsevier (DOI): 10.2299/jsp.25.73 (Tokushima University Institutional Repository: 116447, DOI: 10.2299/jsp.25.73, CiNii: 1390850247496582016)
11.	Shang Ke, Stephen Githinji Karungaru, Chan T. S. Felix, Kenji Terada and Feng Zuren : Two-Stage Robust Optimization for the Orienteering Problem with Stochastic Weights, Complexity, Vol.2020, 1-15, 2020. (Summary) In this paper, the two-stage orienteering problem with stochastic weights is studied, where the first-stage problem is to plan a path under the uncertain environment and the second-stage problem is a recourse action to make sure that the length constraint is satisfied after the uncertainty is realized. First, we explain the recourse model proposed by Evers et al. (2014) and point out that this model is very complex. Then, we introduce a new recourse model which is much simpler with less variables and less constraints. Based on these two recourse models, we introduce two different two-stage robust models for the orienteering problem with stochastic weights. We theoretically prove that the two-stage robust models are equivalent to their corresponding static robust models under the box uncertainty set, which indicates that the two-stage robust models can be solved by using common mathematical programming solvers (e.g., IBM CPLEX optimizer). Furthermore, we prove that the two two-stage robust models are equivalent to each other even though they are based on different recourse models, which indicates that we can use a much simpler model instead of a complex model for practical use. A case study is presented by comparing the two-stage robust models with a one-stage robust model for the orienteering problem with stochastic weights. The numerical results of the comparative studies show the effectiveness and superiority of the proposed two-stage robust models for dealing with the two-stage orienteering problem with stochastic weights. (Keyword) orienteering problem / optimization / stochastic orienteering problem (Tokushima University Institutional Repository) ● Metadata: 115887 (Link to Publication Site) ● Publication site (DOI): 10.1155/2020/5649821 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85097089326 (Tokushima University Institutional Repository: 115887, DOI: 10.1155/2020/5649821, Elsevier: Scopus)
12.	Kohta Sugawara, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : A New Step toward Mastering Double-Under Skill with Supporting Application of Image Processing, The Journal of Information and Systems in Education, Vol.19, No.1, 44-53, 2020. (Tokushima University Institutional Repository) ● Metadata: 115330 (Link to Publication Site) ● Publication site (DOI): 10.12937/ejsise.19.44 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12937/ejsise.19.44 (Tokushima University Institutional Repository: 115330, DOI: 10.12937/ejsise.19.44)
13.	Sharara Elsayed, Akinori Tsuji, Stephen Githinji Karungaru and Kenji Terada : Prediction of the VDT Worker's Headache Using Convolutional Neural Network with Class Activation Mapping, IEEJ Transactions on Electrical and Electronic Engineering, Vol.15, No.11, 1690-1697, 2020. (Summary) 本論文ではVDT作業者の疲労具合を検知するためにカメラ映像から6つの手のポーズを分類する手法を提案する．提案手法では，手のポーズの分類に畳み込みニューラルネットワーク(CNN)をベースとしたディープラーニングを適用している．さらに，顔面上の手のポーズの定位のための分類ネットワークの予測を可視化するためのクラス活性化マップ(CAM)を実装した．有効性を検証する実験で，98.5%の精度で認識できることがわかった． (Keyword) image processing / pattern recognition / health / human sensing (Link to Publication Site) ● Publication site (DOI): 10.1002/tee.23239 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85090460132 (DOI: 10.1002/tee.23239, Elsevier: Scopus)
14.	Shu Yano, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Naoya Kohda, Naka Gotoda and Tomohito Wada : A learning environment of a systematic and tactical style in field sports, --- Basic tactic of an offense team in basketball ---, Transactions of Information Processing Society of Japan, Vol.61, No.3, 657-666, 2020. (Keyword) Tactics comprehension / Team match field sports / computer simulation / basketball (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1050283687644442112 (CiNii: 1050283687644442112)
15.	Stephen Githinji Karungaru, Kenji Matsuura and Naka Gotoda : Ellipse Feature Detection in Rope Skipping for Gross Motor Skill Development, International Journal of Engineering Science and Innovative Technology (IJESIT), Vol.7, No.3, 10-14, 2018. (Summary) To support novice learners to acquire a new skill, it is important to understand the underlying principles ofthe skill. This means that the support system must analyze the skill and develop methods therein to offer credible support toenable efficient learning. This work employs the data from 8 skilled rope skipping subjects to analyze the rope skipping taskto find features that can be used for support. The processes involved include finding the best rope and hand trajectoryfitting using ellipses. This will enable better speed variation detection and timing that can be used to support new learners.In this work, the rope skill attempted is learning to do the double under jump. A double under jump is defined ascompleting two rope rotations per jump. Experimental results prove that this is an effective method for accurate featuredetection and tracking. (Keyword) Ellipse matching / Rope Skipping (Tokushima University Institutional Repository) ● Metadata: 115189 (Tokushima University Institutional Repository: 115189)
16.	Kenji Matsuura, Hiroshi Toyooka, Stephen Githinji Karungaru and Naka Gotoda : Design of a Guide System for Motor Skill Development Targeting a Repetitive Movement Task, The Journal of Information and Systems in Education, Vol.17, No.1, 27-35, 2018. (Tokushima University Institutional Repository) ● Metadata: 111674 (Link to Publication Site) ● Publication site (DOI): 10.12937/ejsise.17.27 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12937/ejsise.17.27 (Tokushima University Institutional Repository: 111674, DOI: 10.12937/ejsise.17.27)
17.	Hossain Mobarok Bhuyain, Stephen Githinji Karungaru, Kenji Terada and Akinori Tsuji : Human Detection and Tracking Using HOG Feature and Particle Filter in Video Surveillance System, International Journal of Advanced Intelligence (IJAI), Vol.9, No.3, 397-407, 2018. (Summary) 監視カメラから得られる映像を用いて，HOG特徴とパーティクルフィルタを用いて人間を抽出し，さらに追跡する手法を提案する．本手法ではHOG特徴を用いて人の領域を抽出し，さらにパーティクルフィルタを用いて人の動きを追跡する．これにより複雑な背景においても，複数の人を同時に検出と追跡することが可能である．本手法の有効性を検証するために，4つのシーンに適用したところ，約90%の検出精度と約99%の追跡精度が得られることがわかった． (Keyword) Video Surveillance System / HOG / Particle Filter / Human Detection and Tracking (Tokushima University Institutional Repository) ● Metadata: 115188 (Tokushima University Institutional Repository: 115188)
18.	Stephen Githinji Karungaru, Tomohiro Ishino and Kenji Terada : Advanced Safety Vehicle (ASV) Technology Driver Support System Monitor using Three Onboard Camera, Journal of the Institute of Industrial Applications Engineers, Vol.6, No.1, 21-28, 2018. (Summary) 本論文では，3台の車載カメラを用いた自動車のドライバーの安全運転を支援する手法を提案した．この手法では，3台の車載カメラのうち前方カメラは歩行者と対向車を，後方カメラでは車線変更の際の後方走行車を，ドライバーカメラでは顔の向きと視線の向きを監視し，それを統合させた情報をドライバーに提示するものである．実際の車載カメラ映像を用いた実験によって，安全運転支援をすることが可能であることがわかった． (Keyword) computer vision / image processing / ITS (Tokushima University Institutional Repository) ● Metadata: 112351 (Link to Publication Site) ● Publication site (DOI): 10.12792/jiiae.6.21 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12792/jiiae.6.21 (Tokushima University Institutional Repository: 112351, DOI: 10.12792/jiiae.6.21)
19.	Stephen Githinji Karungaru, Yamamoto Jumpei and Kenji Terada : Towards Autonomous Driving: Road Surface Signs Recognition using Neural Networks, International Journal of Engineering Research and Technology, Vol.5, No.8, 34-38, 2016. (Summary) In recent years, the number of traffic accidents has rapidly increased for many reasons. However, the most common cause is the driver carelessness and inattentiveness to road signs. Therefore, the aim of this paper is to automatically recognize road surface markings and by availing the information to the driver, hope to reduce road accidents. In the proposed method, the captured image is transformed and edges information used to extract the target road area. The road marking candidate is then extracted and recognized using a neural network. (Keyword) 道路標示 / image processing / neural network / pattern recognition (Tokushima University Institutional Repository) ● Metadata: 115187 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1050004225300384384 (Tokushima University Institutional Repository: 115187, CiNii: 1050004225300384384)
20.	Stephen Githinji Karungaru, Daikoku Masayuki and Kenji Terada : Multi Cameras Based Indoors Human Action Recognition Using Fuzzy Rules, Journal of Pattern Recognition Research, Vol.10, No.1, 61-74, 2015. (Summary) In this paper, the recognition of human actions in an indoor work environment using multi cameras is proposed. HOG features learned using AdaBoost and optimized by background differencing are used to detect the human regions, while the overlapping camera views are merged using perspective transformation. Initially, to recognize a stationary or mobile person, the distance between the detected area in successive frames is used. The direction the person is facing is estimated using the width of the detected region. Several fuzzy rules are then applied to recognize the human actions based on the person's height measured from the direction they are facing. In addition, suspicious action is recognized using the presence of an abandoned object and detection duration. In experiments, recognition accuracies achieved for "walking" , "stop", running", "sitting", "desk working" and "falling" actions are 87%, 92% , 46%, 95%, 89%, and 91% respectively. (Keyword) image processing / HOG特徴量 / human sensing (Link to Publication Site) ● Publication site (DOI): 10.13176/11.651 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.13176/11.651 (DOI: 10.13176/11.651)
21.	Stephen Githinji Karungaru, Nakano Hitoshi and Minoru Fukumi : Road Traffic Signs Recognition using Genetic Algorithms and Neural Networks, International Journal of Machine Learning and Computing, Vol.3, No.3, 313-317, 2013. (Link to Publication Site) ● Publication site (DOI): 10.7763/IJMLC.2013.V3.329 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.7763/IJMLC.2013.V3.329 (DOI: 10.7763/IJMLC.2013.V3.329)
22.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Detection of Abandoned Luggage and Owner Tracking at Sensitive Public Areas, IEEJ Transactions on Electronics, Information and Systems, Vol.133-C, No.1, 67-73, 2012. (Summary) Abandoned objects in sensitive congested public areas like airports or train stations pose a major security threat. Therefore, in this paper, to solve the problem, we propose a novel method for the detection of abandoned luggage, tracking its owner and extracting any other necessary information using multi-threshold pixel based dynamic background model and Earth Mover's Distance (EMD) signature matching. The public area selected for experiments is a train station. The background model is created by learning the color variance in all pixels by allowing multiple thresholds per pixel. After learning, pruning unnecessary thresholds improves the foreground extraction speed. Blob noise and outliers including shadows are deleted by a binarization method based on the Discriminant Analysis (DA) method. A color signature created using the HSV color space that is fast to process, is matched using the EMD metric to track blobs. Once an abandoned object candidate is found, a slower but more accurate SURF algorithm is used to extract feature points for further tracking. Stationary objects after this phase are considered to be abandoned luggage. To prove the effectiveness of the proposed method, experiments are conducted using the i-Lids dataset (2007 IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS 2007)) achieving a frame-based average accuracy of about 93%. (Keyword) Luggage owner / Active background / abandoned objects / Earth Mover's Distance / Discriminant Analysis (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.133.67 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84873809059 (DOI: 10.1541/ieejeiss.133.67, Elsevier: Scopus)
23.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Automatic Background Updating for Abandoned Object Detection at Train Stations, International Journal of Machine Learning and Computing, Vol.2, No.5, 609-613, 2012. (Summary) In video surveillance using overhead cameras, it is very important to capture and regularly updated the background to enable accurate extraction of persons or objects of interest. However, in scenes with a lot of movement and stationary objects, for example a train station, it is not easy to update the background without including such objects. In this work, we investigate several objects features and combine them to maintain a stable background image. The features include the speed of the object, texture, shape, associations between persons and objects, etc. The data used is a subset of the i-Lids dataset that was captured for analyzing video systems. It is captured in a train station using one overhead camera. Each video segment is about three minutes long. Index TermsActive background, abandoned objects, shape matching. (Keyword) image processing / オーバーヘッドカメラ / 背景画像更新 (Link to Publication Site) ● Publication site (DOI): 10.7763/IJMLC.2012.V2.199 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.7763/IJMLC.2012.V2.199 (DOI: 10.7763/IJMLC.2012.V2.199)
24.	Stephen Githinji Karungaru, Ishitani Atsushi, Shiraishi Takuya and Minoru Fukumi : A Simple Interface for Mobile Robot Equipped with Single Camera using Motion Stereo Vision, International Journal of Machine Learning and Computing, Vol.2, No.5, 633-639, 2012. (Link to Publication Site) ● Publication site (DOI): 10.7763/IJMLC.2012.V2.204 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.7763/IJMLC.2012.V2.204 (DOI: 10.7763/IJMLC.2012.V2.204)
25.	Stephen Githinji Karungaru, Yoshida Toshihiro, Seo Toru, Minoru Fukumi and Kenji Terada : Monotonous Tasks and Alcohol Consumption effects on the Brain by EEG Analysis using Neural Networks, International Journal of Computational Intelligence and Applications, Vol.11, No.3, 1250015, 2012. (Summary) An analysis of the Electroencephalogram (EEG) signals while performing a monotonous task and drinking alcohol using principal component analysis (PCA), linear discriminant analysis (LDA) for feature extraction and Neural Networks (NNs) for classification is proposed. The EEG is captured while performing a monotonous task that can adversely affect the brain and possibly cause stress. Moreover, we investigate the effects of alcohol on the brain by capturing the data continuously after consumption of equal amounts of alcohol. We hope that our work will shed more light on the relationship between such actions and EEG, and investigate if there is any relation between the tasks and mental stress. EEG signals offers a rare look at brain activity, while, monotonous activities are well known to cause irritation which may contribute to mental stress. We apply PCA and LDA to characterize the change in each component, extract it and discriminate using a NN. After experiments, it was found that PCA and LDA are effective analysis methods in EEG signal analysis. (Keyword) electroencephalogram / stress / PCA / neural network (Link to Publication Site) ● Publication site (DOI): 10.1142/S1469026812500150 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.1142/S1469026812500150 (DOI: 10.1142/S1469026812500150)
26.	Hemdan Ibrahim, Stephen Githinji Karungaru and Kenji Terada : Video Surveillance using Facial Features-based Tracking, International Journal of Innovative Computing, Information and Control, Vol.8, No.4, 2761-2776, 2012. (Summary) In this work, we present a real time system for facial features detection and tracking in image sequences. We are interested in developing a human tracking system that can improve human-computer interaction and benefit video surveillance problems by making it invariant to rotation, illumination and subject's movement. However, since human body and face movements are very complicated to detect and track, all available cues that can narrow the search space should be considered. This paper describes a novel strategy for both face tracking and facial feature detection. Face detection is important because it reduces the search space and consequently saves time for further face processing, e.g. recognition or transmission. Moreover, facial feature detection enables face normalization which leads to size invariant face recognition. The proposed face tracker resembles human perception in that, initially, it utilizes motion as the major cue and thereafter, searches for the eyes in the areas likely to contain human faces. The presence of a face is determined using an eye tracker. Eyes are important facial features due to their relatively constant interocular distance. In this work, efficiency improvement focuses on two points: reducing template matching area and speeding up the matching process. Our method initially detects two rough eye candidate regions using a feature based method. All other processes are thereafter performed inside the candidate regions. In addition, we can evaluate the size of eye template according to the size of the regions. Altogether, the proposed method combines the accuracy of template based methods and the efficiency of feature based methods in the visual spectrum. To prove the effectiveness of this approach, we performed comparative experiments using real video images. We achieved a real time detection accuracy of about 96%. (Keyword) image processing / computer vision / pattern recognition / security (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84859178522 (Elsevier: Scopus)
27.	H.K. Choge, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : A Local DCT-II Feature Extraction Approach for personal Identification Based on Palmprint, IEEJ Transactions on Electronics, Information and Systems, Vol.130-C, No.9, 1657-1666, 2010. (Summary) Biometric applications based on the palmprint have recently attracted increased attention from various researchers. In this paper, a method is presented that differs from the commonly used global statistical and structural techniques by extracting and using local features instead. The middle palm area is extracted after preprocessing for rotation, position and illumination normalization. The segmented region of interest is then divided into blocks of either 8×8 or 16×16 pixels in size. The type-II Discrete Cosine Transform (DCT) is applied to transform the blocks into DCT space. A subset of coefficients that encode the low to medium frequency components is selected using the JPEG-style zigzag scanning method. Features from each block are subsequently concatenated into a compact feature vector and used in palmprint verification experiments with palmprints from the PolyU Palmprint Database. Results indicate that this approach achieves better results than many conventional transform-based methods, with an excellent recognition accuracy above 99% and an Equal Error Rate (EER) of less than 1.2% in palmprint verification. (Keyword) palmprint recognition / local DCT / biometric feature extraction / hand-based biometrics (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.130.1657 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390282679586217216 ● Search Scopus @ Elsevier (DOI): 10.1541/ieejeiss.130.1657 (DOI: 10.1541/ieejeiss.130.1657, CiNii: 1390282679586217216)
28.	Stephen Githinji Karungaru, Kamei Tomoaki, Fujiwara Masato, Norio Akamatsu and Minoru Fukumi : Vowel Recognition Using Akamatsu Integral and Differential Transforms, International Journal of Advanced Intelligence (IJAI), Vol.1, No.1, 125-140, 2009.
29.	Hillary Kipsang Choge, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Development of a Block based Palmprint Recognition Methodology Using the Discrete Cosine Transform, Australian Journal of Intelligent Information Processing Systems, Vol.10, No.4, 22-31, 2009. (Summary) Hand-based biometric applications based on the palmprint have recently become a popular choice due to their high acceptance by the general public. In this paper, a method is presented which applies the type-II Discrete Cosine Transform (DCT) in a novel way by extracting selected coefficients from small overlapping blocks of scanned, medium-resolution palmprint images to form a feature vector for personal identification. The middle palm area is extracted after rotation, position and illumination normalization during the preprocessing stage before dividing it into 8×8 pixel blocks. The type-II DCT is then used to transform the blocks, and only a small set of the coefficients selected from each block after ranking based on magnitude only. The selected coefficients are concatenated to create a compact feature vector that represents each palmprint. Experiments using a subset of the PolyU Palmprint Database show that this block-based approach effectively discriminates between palmprints, with excellent palmprint recognition results and an Equal Error Rate (EER) of less than 2% in palmprint authentication when using a 64×64 pixel input image block.
30.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Fast Approximate Incremental Learning Algorithm based on of Simple-FLDA, Journal of Signal Processing, Vol.13, No.6, 515-523, 2009. (Summary) This paper presents an Incremental Simple-FLDA. The Incremental Simple-FLDA is a fast incremental learning algorithm based on Simple-FLDA. This algorithm need not hold all training samples because it enables update of an eigenvector according to incremental samples. Moreover, this algorithm has an advantage that it can calculate the eigenvector at high-speed because matrix calculation is not needed. We performed computer simulations using UCI datasets, EMG data and face data to verify the effectiveness of the proposed algorithm. As a result, its availability was confirmed from the standpoint of recognition accuracy and convergence performance of the eigenvector compared with the other methods. (Keyword) linear discriminant analysis / incremental learning / dimensional reduction / biological signal / face recognition (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1521417755349060608 (CiNii: 1521417755349060608)
31.	Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Takuya Akashi : Detection and Recognition of Vehicle License Plates Using Template Matching, Genetic Algorithms and Neural Networks, International Journal of Innovative Computing, Information and Control, Vol.5, No.7, 1975-1985, 2009. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-67749108064 (Elsevier: Scopus)
32.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Interactive Interface with Evolutionary Eye Sensing and Physiological Knowledge, IEEJ Transactions on Electronics, Information and Systems, Vol.129-C, No.7, 1288-1295, 2009. (Summary) The purpose of this study is to develop an interactive interface using eye movement to operate a welfare apparatus, such as a feeding device for an orthopedically-impaired person. A part of the purpose is to eliminate special calibration and re-calibration during the operation. Originalities of this proposed system are as follows: eye sensing with evolutionary processing and interactive operation screen based on some physiological knowledge. The proposed system uses a non-contact type interface by the eye movement. An iris is tracked and eye movement is measured by the evolutionary eye sensing (EES) method. An operation screen is divided into 9 areas, which has visual stimulation using the physiological knowledge. A user can select these areas by eye movement and decide by eye fixation. The effectiveness of the proposed system is evaluated by comparison experiments with 20 subjects. The results indicate that the proposed system is easy to use for first-timer, who can become proficient in operation just after a few exercises. (Keyword) computer vision / Welfare Apparatus System / human interface / Evolutionary Video Processing (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.129.1288 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390001204604580352 ● Search Scopus @ Elsevier (DOI): 10.1541/ieejeiss.129.1288 (DOI: 10.1541/ieejeiss.129.1288, CiNii: 1390001204604580352)
33.	Choge Kipsang Hillary, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : A DFT-Based Method of Feature Extraction for Palmprint Recognition, IEEJ Transactions on Electronics, Information and Systems, Vol.129-C, No.7, 1296-1304, 2009. (Summary) Over the last quarter century, research in biometric systems has developed at a breathtaking pace and what started with the focus on the fingerprint has now expanded to include face, voice, iris, and behavioral characteristics such as gait. Palmprint is one of the most recent additions, and is currently the subject of great research interest due to its inherent uniqueness, stability, user-friendliness and ease of acquisition. This paper describes an effective and procedurally simple method of palmprint feature extraction specifically for palmprint recognition, although verification experiments are also conducted. This method takes advantage of the correspondences that exist between prominent palmprint features or objects in the spatial domain with those in the frequency or Fourier domain. Multi-dimensional feature vectors are formed by extracting a GA-optimized set of points from the 2-D Fourier spectrum of the palmprint images. The feature vectors are then used for palmprint recognition, before and after dimensionality reduction via the Karhunen-Loeve Transform (KLT). Experiments performed using palmprint images from the `PolyU Palmprint Database' indicate that using a compact set of DFT coefficients, combined with KLT and data preprocessing, produces a recognition accuracy of more than 98% and can provide a fast and effective technique for personal identification. (Keyword) palmprint recognition / biometrics / DFT feature extraction / GA optimization (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.129.1296 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390282679581288320 ● Search Scopus @ Elsevier (DOI): 10.1541/ieejeiss.129.1296 (DOI: 10.1541/ieejeiss.129.1296, CiNii: 1390282679581288320)
34.	Stephen Githinji Karungaru, Takuya Akashi, Nakano Miyoko and Minoru Fukumi : Hour-glass Neural Network based Daily Money Flow Estimation for Automatic Teller Machines, IEEJ Transactions on Electronics, Information and Systems, Vol.129-C, No.7, 1325-1330, 2009. (Summary) Monetary transactions using Automated Teller Machines (ATMs) have become a normal part of our daily lives. At ATMs, one can withdraw, send or debit money and even update passbooks among other many possi- ble functions. ATMs are turning the banking sector into a ubiquitous service. However, while the advantages for the ATM users (Financial institution customers) are many, the Financial institution side faces an uphill task in management and maintaining the cash flow in the ATMs. On one hand, too much money in a rarely used ATM is wasteful, while on the other, insuficient amounts would adversely affect the customers and may result in a lost business opportunity for the financial institution. Therefore, in this paper, we propose a daily cash flow estimation system using neural networks that enables better daily forecasting of the money required at the ATMs. The neural network used in this work is a fiveve layered hour glass shaped structure that achieves fast learning, even for the time series data for which seasonality and trend feature extraction is difficult. Feature extraction is carried out using the Akamatsu Integral and Differential transforms. This work achieves an average estimation accuracy of 92.6%. (Keyword) ATMs / Neural Networks / Cash Flow Estimation / Time series / Akamatsu Transform (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.129.1325 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390282679581335168 ● Search Scopus @ Elsevier (DOI): 10.1541/ieejeiss.129.1325 (DOI: 10.1541/ieejeiss.129.1325, CiNii: 1390282679581335168)
35.	Stephen Githinji Karungaru, Takuya Akashi, Minoru Fukumi and Norio Akamatsu : Image Morphing and Warping: Application to Speech Simulation using a Single Image, Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.13, No.4, 441-446, 2009. (Link to Publication Site) ● Publication site (DOI): 10.20965/jaciii.2009.p0441 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-77749314586 (DOI: 10.20965/jaciii.2009.p0441, Elsevier: Scopus)
36.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Fast Incremental Algorithm of Simple Principal Component Analysis, IEEJ Transactions on Electronics, Information and Systems, Vol.129, No.1, 112-117, 2009. (Summary) This paper presents a new algorithm for incremental learning, which is named Incremental Simple-PCA. This algorithm adds an incremental learning function to the Simple-PCA that is an approximation algorithm of the principal component analysis where an eigenvector can be calculated by a simple repeated calculation. Using the proposed algorithm, it is possible to update the eigenvector faster by using incremental data. We carry out computer simulations on personal authentication that uses face images and wrist motion recognition that uses wrist EMG by incremental learning to verify the effectiveness of this algorithm. These results were compared with the results of Incremental PCA that introduced incremental learning function to the conventional PCA. (Keyword) PCA / Simple-PCA / Incremental PCA / Incremental Simple-PCA / Incremental learning (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.129.112 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390282679581905920 ● Search Scopus @ Elsevier (DOI): 10.1541/ieejeiss.129.112 (DOI: 10.1541/ieejeiss.129.112, CiNii: 1390282679581905920)
37.	Takuya Akashi, Koh Nakamichi, Stephen Githinji Karungaru, Yasue Mitsukura, Kanya Tanaka and Minoru Fukumi : Liver tumor extraction from CT images using genetic algorithm, Journal of Signal Processing, Vol.13, No.1, 67-76, 2009. (Summary) 本論文では，腹部X線CT画像における医師への診断補助システムの構築である．その第一歩として，1スライスのX線CT画像内の病変可能性が最も高い個所を自動的に抽出する領域分割手法を提案している．形状認識の点から，動的輪郭決定手法としてSnakesやLive-wireといった手法が提案されているが，これらの手法は輪郭が不明瞭でCT値も未知な腫瘍に対して効果的ではない．本論文では，遺伝的アルゴリズムにより腫瘍領域形状を最適化する方法を提案している．計算機実験により，その有効性を評価している． (Keyword) medical image / genetic algorithm / liver tumor
38.	Stephen Githinji Karungaru, Fukuda Keiji, Minoru Fukumi and Norio Akamatsu : Fingerprints Images Enhancement Using a Concavity and Convexity method, Biomedical Soft Computing and Human Sciences, Vol.14, No.1, 39-46, 2008.
39.	Choge Kipsang Hillary, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Enhancement of Palmprint Images Using an Optimized Hexagonal Multilayer Perceptron Neural Network, Journal of Signal Processing, Vol.12, No.6, 449-456, 2008.
40.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Evolutionary Video Processing for Lips Tracking, International Journal of Intelligent Computing in Medical Sciences and Image Processing, Vol.2, No.2, 111-125, 2008. (Summary) In this paper, real-time tracking and information acquisition of lip region of a person during speech in active video scenes are addressed. The lip is deformed by speech, and the size and orientation are changed by camera motion. The difficulty is mainly due to change of these appearances of the lip. We use template matching with a genetic algorithm to overcome these problems. A high speed and accurate tracking scheme using Evolutionary Video Processing is proposed. Usually, a genetic algorithm is unsuitable for a tracking accuracy of 91.6% and an average processing time of 26.0 milliseconds per frame are achieved. (Link to Publication Site) ● Publication site (DOI): 10.1080/1931308X.2008.10644159 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84872781664 (DOI: 10.1080/1931308X.2008.10644159, Elsevier: Scopus)
41.	Stephen Githinji Karungaru, Minoru Fukumi, Takuya Akashi and Norio Akamatsu : Genetic Algorithms based Adaptive Search Area Control for Real Time Multiple Face Detection using Neural Networks, WSEAS Transactions on Signal Processing, Vol.4, 97-109, 2008. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-48849106824 (Elsevier: Scopus)
42.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Downsized Evolutionary Video Processing for Lips Tracking and Data Acquisitiong, JACIII SCIS&ISIS2006, Vol.11, No.8, 1030-1042, 2007. (Summary) In this paper, high-speed lips tracking and data acquisition of a talking person in natural scenes are presented. Our approach is based on the Evolutionary Video Processing. This method has a trade-off between accuracy and a processing time. To solve this problem, in this paper, we proposed Evolutionary Video Processing with automatic SD-Control. In our simulations, the effectiveness of the proposed method is verified by a comparison experiment. The proposed method improves the performance, speed and accuracy, from 68.4% to 86.2%. Furthermore, it is evaluated that our proposed method can continue to chase the lips region even in such a case. It is demonstrated that the lips region detection and tracking at high speed and with high accuracy is possible, with acquisition of its numerical geometric change information.
43.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : High Speed Genetic Lips Detection by Dynamic Search Domain Control, IEEJ Transactions on Electronics, Information and Systems, Vol.127, No.6, 854-866, 2007. (Summary) In this paper, high-speed size and orientation invariant lips detection of a talking person in an active scene using template matching and genetic algorithms is proposed. As part of the objectives, we also try to acquire numerical parameters to represent the lips. The information is very important for many applications, where high performance is required, such as audio-visual speech recognition, speaker identification systems, robot perception and personal mobile devices interfaces. The difficulty in lips detection is mainly due to deformations and geometric changes of the lips during speech and the active scene by free camera motion. In order to enhance the performance in speed and accuracy, initially, the performance is improved on a single still image, that is, the base of video processing. Our proposed system is based on template matching using genetic algorithms (GA). Only one template is prepared per experiment. The template is the closed mouth of a subject, because the application is for personal devices. In our previous study, the main problem was trade-off between search accuracy and search speed. To overcome this problem, we use two methods: scaling window and dynamic search domain control (SD-Control). We therefore focus on the population size of the GA, because it has a direct effect on search accuracy and speed. The effectiveness of the proposed system is demonstrated by performing computer simulations. We achieved a lips detection accuracy of 91.33% at an average processing time of 33.70 milliseconds per frame. (Keyword) genetic algorithm / Template matching / Lips image / Scaling window / Dynamic search domain control (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.127.854 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390001204606322816 ● Summary page in Scopus @ Elsevier: 2-s2.0-34250001711 (DOI: 10.1541/ieejeiss.127.854, CiNii: 1390001204606322816, Elsevier: Scopus)
44.	Tadahiro Oyama, Yuji Matsumura, Stephen Githinji Karungaru and Minoru Fukumi : Feature Generation Method by Geometrical Interpretation of Fisher Linear Discriminant Analysis, IEEJ Transactions on Electronics, Information and Systems, Vol.127, No.6, 831-836, 2007. (Summary) This paper presents a new algorithm for feature generation, which is derived based on geometrical interpretation of the fisher linear discriminant analysis (FLDA). This algorithm (Simple-FLDA) is an approximation algorithm that calculates eigenvectors sequentially by an easy iterative calculation by expressing the maximization of variance between classes and minimization of variance in each class without the use of matrix calculation. We carry out computer simulations about recognition of wrist motion patterns by EMG measured from wrist and personal authentications that use face images to verify the effectiveness of this technique. The result was compared with the result of principal component analysis (Simple-PCA). (Keyword) simple-FLDA / simple-PCA / pattern recognition / electromyogram activity / face recognition / feature generation (Link to Publication Site) ● Publication site (DOI): 10.1541/ieejeiss.127.831 (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390282679583034752 ● Summary page in Scopus @ Elsevier: 2-s2.0-34249985813 (DOI: 10.1541/ieejeiss.127.831, CiNii: 1390282679583034752, Elsevier: Scopus)
45.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Using Genetic Algorithm for Eye Detection and Tracking in Video Sequence, Journal of Systemics, Cybernetics and Informatics, Vol.5, No.2, 72-78, 2007. (Summary) We propose a high-speed size and orientation invariant eye tracking method, which can acquire numerical parameters to represent the size and orientation of the eye. In this paper, we discuss that high tolerance in human head movement and real-time processing that are needed for many applications, such as eye gaze tracking. The generality of the method is also important. We use template matching with genetic algorithm, in order to overcome these problems. A high speed and accuracy tracking scheme using Evolutionary Video Processing for eye detection and tracking is proposed. Usually, a genetic algorithm is unsuitable for a realtime processing, however, we achieved real-time processing. The generality of this proposed method is provided by the artificial iris template used. In our simulations, an eye tracking accuracy is 97.9% and, an average processing time of 28 milliseconds per frame.
46.	Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Akashi Takuya : Automatic Human Faces Morphing Using Genetic Algorithms Based Control Points Selection, International Journal of Innovative Computing, Information and Control, Vol.3, No.2, 247-256, 2007. (Keyword) genetic algorithms / morphing / warping / neural networks / face detection (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-48249099120 (Elsevier: Scopus)
47.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Genetic Eye Detection Using Artificial Template, Journal of Signal Processing, Vol.10, No.6, 453-464, 2006. (Keyword) image understanding / genetic algorithm / template matching / eye detection / human interface (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1520010380937736704 (CiNii: 1520010380937736704)
48.	Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Takuya Akashi : Optimizing Feature Extraction for the Camera Mouse using Genetic Algorithms, WSEAS Transactions on Computers, Vol.5, No.11, 2722-2725, 2006. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-33746868903 (Elsevier: Scopus)
49.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Genetic Algorithms Based On-line Size and Rotation Invariant Face Detection, Journal of Signal Processing, Vol.9, No.6, 497-503, 2005.
50.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Face Recognition in Color Images Using Neural Networks and Genetic Algorithms, International Journal of Computational Intelligence and Applications, Vol.5, No.1, 55-67, 2005. (Link to Publication Site) ● Publication site (DOI): 10.1142/S1469026805001477 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.1142/S1469026805001477 (DOI: 10.1142/S1469026805001477)
51.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Morphing Human Faces: Automatic Control Points selection and Color Transition, Trans. on Engineering Computing and Technolog, Vol.1, No.1, 224-227, 2004.
52.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Skin Color Correction through Illuminant Estimation Using Neural Networks and Analytical Methods, Journal of Signal Processing, Vol.7, No.1, 69-78, 2003. (Summary) 本論文は，カラー画像中の顔(肌色部分)を対象として．過露光や露光不足などの光温度が極端に異なる場合の肌色の補正方法を提案している．顔領域を正確に抽出する場合には，顔の肌色範囲を正確に指定することが重要であり，その前処理として肌色部分の色補正を行う方法を提案している．特にニューラルネットワークの学習と円柱座標系での距離計算に基づく補正方法により，高精度に肌色情報を補正し，顔領域を検出できることを計算機シミュレーションにより定量的に検証した．
53.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Human Face Detection in Visual Scenes Using Neural Networks, IEEJ Transactions on Electronics, Information and Systems, Vol.122-C, No.6, 995-1000, 2002. (Summary) 本論文は，カラー画像中から人間の顔を検出するための高速·高精度な方法を提案している．特に，顔の特徴である肌色情報をニューラルネットワークにより学習検出し，後処理の顔判定を行う領域を低減させ高速化を達成している．後処理では顔の幾何学的特徴を別のニューラルネットワークで学習し，かつ構造化学習によりニューラルネットワークの構造を最小化し，高精度と高速を同時に失言している．カラー画像での計算シミュレーションにより，複数顔が含まれる場合でも高精度に顔検出できることを示した． (Keyword) Back propagation / Self- organizing maps / Down-sampling / Merging overlapping detections (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1390001204609798400 (CiNii: 1390001204609798400)

Academic Letter:

1.	Takehiko Yoshikawa, Kenji Matsuura, Kohta Sugawara, Stephen Githinji Karungaru and Naka Gotoda : Supporting Stabilization of Timing Difference between Coordinated Motor Actions in Double-under by Sensing Multiple Body Parts, Japan Journal of Educational Technology, Vol.41, No.Suppl., 229-232, 2017. (Tokushima University Institutional Repository) ● Metadata: 111527 (Link to Publication Site) ● Publication site (DOI): 10.15077/jjet.S41118 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.15077/jjet.S41118 (Tokushima University Institutional Repository: 111527, DOI: 10.15077/jjet.S41118)

Proceeding of International Conference:

1.	Kenji Matsuura, Hironori Takeuchi, Urushihara Kazuki, Hiroki Tanioka, Stephen Githinji Karungaru and Tomohito Wada : Multiplayer Tracking with Diagonal Video to Support Basketball Tactical Learning, 18th International Conference on Ubiquitous Information Management and Communication, 5pgs, Kuala Lumpur, Malaysia, Jan. 2024. (Summary) Player tracking has become a crucial technique for getting strategic advantage in competitive team sports. Movies captured by one or a few cameras are easy to use for this purpose at any level including amateur. This study describes a design issue that integrates up-to-date technologies of multi-object tracking for tactics detection from the actual game data to bring affordability, feasibility, and accessibility. (Keyword) multi-object-tracking / basketball / tactics / learning
2.	Sonom-Ochir Ulziibayar, Stephen Githinji Karungaru, Kenji Terada and Ayush Altangerel : Dashboard-camera-based Safe Driving Support System, The 8th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science Engineering (BCD 2023), 1-5, Dec. 2023. (Keyword) pattern recognition / image processing / deep learning
3.	Stephen Githinji Karungaru, Kenji Matsuura and Hiroki Tanioka : Basketball Players Identification and Tracking using a Single Fixed Camera, 17th International Conference on Signal Image Technology & Internet based Systems, 342-347, Bangkok, Nov. 2023. (Summary) The application of data science in sports has recentlygained significant importance. Consequently, tactics development,opponent team understanding, in-game decision-making, playervital statistics, etc. could all benefit from game data analysis.Given a video input, this study proposes employing consecutiveintersection over union (IOU) based tracking and K-Meansbased uniform colors detection methods to monitor players andidentify teams in basketball. A retrained YOLOv7 algorithmis used to recognize the humans (players, referees, etc.), ball,and field markers. The Kalman filter is employed to tackleocclusion occurrence during tracking. Our findings indicate thatthis technology may be practical and affordable for both amateurand professional teams. (Keyword) multi-object-tracking / basketball / tactics / machine learning
4.	Khalzaa Khulan, Stephen Githinji Karungaru and Kenji Terada : Creation and Testing of Synthetic Datasets for Training Road Scenes Algorithms, 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Vol.WeBT6.3, 1-6, Busan, Aug. 2023. (Keyword) pattern recognition / image processing / deep learning / Smart driving
5.	HASSAN MEHEDI MOHAMMAD, Stephen Githinji Karungaru and Kenji Terada : Recognizing football game events: Handball based on Computer Vision, 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Vol.TuET6.9, 1-6, Busan, Aug. 2023. (Keyword) pattern recognition / image processing / deep learning
6.	Hiroki Tanioka, Miura Tsuyoshi, Kenji Matsuura and Stephen Githinji Karungaru : Development of semi-automatic image annotation using object recognition, Proceedings of IIAI-AAI2023, Koriyama, Jul. 2023. (Summary) The modern field of machine learning has made remarkable progress, and the demand for training data required by machine learning systems is constantly increasing. However, the annotation work required to create this training data requiresa great deal of effort. Therefore, we considered semi-automating the labeling process by taking advantage of false positives that occur when object detection is performed by YOLOv5, thereby eliminating the need for region selection and reducing the cost of annotation work. In a comparison experiment with labelImg, a common annotation tool, we found that semi-automating the annotation process took less time than manually annotating the objects. (Keyword) machine learning / image recognition / annotation / labeling
7.	SHI ZHIWEI, Stephen Githinji Karungaru and Kenji Terada : Image-based Pretreatment Study of Rice Blast Disease, 3rd International Conference on Intelligent Systems, Cognitive Science and Knowledge Engineering, 1-12, May 2023. (Summary) Rice blight has a great impact on rice yield and can lead to yield reduction of up to 70% in severe cases. Traditional detection methods require professional technicians to operate and are costly and inefficient, and cannot detect rice diseases in real-time. In this paper, we applied image detection technology to study rice blast disease based on the Matlab platform. Firstly, a basic rice blast database is built, and then a discussion is made on how to effectively improve the recognition success rate of rice blast images by two aspects: image pre-processing and feature extraction. The main research contents are as follows. (1) After studying the existing plant disease database, a basic rice blast database was constructed by field photography and other means. (2) Preprocessing of the collected rice blight images. Using the algorithm of rgb2gray function in Matlab, the images were grayed out; based on this, median filtering was used for noise reduction; then histogram equalization technique was used for image enhancement to increase the contrast and make the images clear; finally, various segmentation algorithms were used for image segmentation. (3) For the pre-processed rice blight images, feature extraction was performed in terms of the color of the disease to pave the way for feature selection. (Keyword) Rice blight
8.	WANG MEIQING, Stephen Githinji Karungaru and Kenji Terada : Pedestrian detection algorithm based on improved YOLOv3, 3rd International Conference on Intelligent Systems, Cognitive Science and Knowledge Engineering, 1-12, May 2023. (Summary) The ability to accurately detect pedestrians in the area of interest in real time is crucial in the field of autonomous driving. An improved YOLOv3 model is proposed for pedestrian detection. Firstly, a lightweight model that incorporates a residual network module approach and a CBAM attention mechanism is added to the structure to enhance the feature representation capability of the network. Experimental results show that the improved YOLOv3 target detection model raises the detection accuracy by 4% compared to the original algorithm, and the accuracy precision is improved to a large extent, which verifies the feasibility and effectiveness of the improved YOLOv3 model for pedestrian detection. (Keyword) Pedestrian detection / YOLOv3
9.	Haoran Ji, Stephen Githinji Karungaru and Kenji Terada : Indoors Fitness Training Monitoring based on OpenPose, 3rd International Conference on Intelligent Systems, Cognitive Science and Knowledge Engineering, 1-12, May 2023. (Summary) With the continuation of the COVID-19 pandemic, people's daily life has changed. The changing life habits are reflected in the increasing number of hours working at home. Mostly affected is physical fitness, because of limitations or fear of the gym/outdoors or effective exercise indoors. However, with the arrival of the post-pandemic era, although working at home has improved, the fitness problem still haunts people. Some people have become accustomed to home fitness and are no longer limited to the traditional gym or gymnasium. However, proper and safe exercising is still a challenge due to the lack of live coaching. With the advent of artificial intelligence and the improvement of virtual reality (VR) and augmented reality (AR) capabilities, the options for live off-site coaching have become feasible. This study is based on OpenPose technology in artificial intelligence to monitor the standard of people's movements in-home fitness. The study results are encouraging. (Keyword) Pose Recognition / Fitness / Movement Analysis
10.	GU MINGCEN, Stephen Githinji Karungaru and Kenji Terada : Vision-based primary localization method for SLAM mobile robots, 3rd International Conference on Intelligent Systems, Cognitive Science and Knowledge Engineering, 1-12, Aurangabad, May 2023. (Summary) The AMCL (Adaptive Monte Carlo Localization) algorithm with visual provision of initial values is proposed to address the slow localization speed caused by conventional laser SLAM (Simultaneous Localization and Mapping) without initial poses and the global localization failure after a robot abduction event. In the initial map building phase, the ORB (Oriented FAST and Rotated BRIEF) feature values are extracted from the camera and the wall corners are identified, and then the pose information is stored in the database and a feature dictionary is constructed. After restarting, the dictionary is called to perform loopback detection by receiving the images captured by the current camera, and a successful detection results in a rough initial pose. If the detection fails, the initial pose is roughly calculated by identifying the wall corners. Finally, the particle filtering algorithm scatters particles in a small area near the obtained pose and converges to obtain a relatively accurate pose. (Keyword) machine learning / image recognition / robot / labeling
11.	HASSAN MEHEDI MOHAMMAD, Stephen Githinji Karungaru and Kenji Terada : Application of On-Road Surveillance Cameras for Traffic Light Optimization, Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS2022), 1-6, Nov. 2022. (Keyword) pattern recognition / image processing / deep learning (Link to Publication Site) ● Publication site (DOI): 10.1109/SCISISIS55246.2022.10001932 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85146663732 (DOI: 10.1109/SCISISIS55246.2022.10001932, Elsevier: Scopus)
12.	Sonom-Ochir Ulziibayar, Stephen Githinji Karungaru, Kenji Terada and Ayush Altangerel : Appearance-based Drivers Gaze Mapping Using a Dash Camera, Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS2022), 1-5, Nov. 2022. (Keyword) pattern recognition / image processing / deep learning (Link to Publication Site) ● Publication site (DOI): 10.1109/SCISISIS55246.2022.10001875 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85146665267 (DOI: 10.1109/SCISISIS55246.2022.10001875, Elsevier: Scopus)
13.	Stephen Githinji Karungaru, Hiroki Tanioka and Kenji Matsuura : Soccer Players Real Location Determination Using Perspective Transformation, Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS2022), 1-4, Nov. 2022. (Keyword) pattern recognition / image processing / deep learning (Link to Publication Site) ● Publication site (DOI): 10.1109/SCISISIS55246.2022.10001939 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85146676613 (DOI: 10.1109/SCISISIS55246.2022.10001939, Elsevier: Scopus)
14.	Rong Chen and Stephen Githinji Karungaru : Multi-modal Feature Fusion Network for Breast Lesions Segmentation, The 18th International Conference on Intelligent Unmanned Systems, 1-6, Aug. 2022. (Keyword) pattern recognition / image processing / deep learning / ITS
15.	Hassan Mehedi Mohammad, Stephen Githinji Karungaru and Kenji Terada : An intelligent traffic control systems using on-road cameras, Proceedings of SPIE, Vol.11794, No.117941C, Online, Jul. 2021. (Keyword) image processing / pattern recognition / VR (Link to Publication Site) ● Publication site (DOI): 10.1117/12.2589192 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85112473228 (DOI: 10.1117/12.2589192, Elsevier: Scopus)
16.	ORGIL JARGALSAIKHAN, Stephen Githinji Karungaru and Kenji Terada : Continual learning : Linear layer classier concatenation using image processing transform functions, Proceedings of SPIE, Vol.11794, No.117941A, Online, Jul. 2021. (Keyword) image processing / pattern recognition / VR (Link to Publication Site) ● Publication site (DOI): 10.1117/12.2589077 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85112430291 (DOI: 10.1117/12.2589077, Elsevier: Scopus)
17.	Nsinga Robert, Stephen Githinji Karungaru and Kenji Terada : A comparative study of batch ensemble for multi-object tracking approximations in embedded vision, Proceedings of SPIE, Vol.11794, No.1179410, Online, Jul. 2021. (Keyword) image processing / pattern recognition / VR (Link to Publication Site) ● Publication site (DOI): 10.1117/12.2589037 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85112476584 (DOI: 10.1117/12.2589037, Elsevier: Scopus)
18.	ERDENE NANDIN ERDENEBAATAR, Stephen Githinji Karungaru and Kenji Terada : Social distance measurement for indoor environments, Proceedings of SPIE, Vol.11794, No.117940T, Online, Jul. 2021. (Keyword) image processing / pattern recognition / VR (Link to Publication Site) ● Publication site (DOI): 10.1117/12.2589105 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85112455174 (DOI: 10.1117/12.2589105, Elsevier: Scopus)
19.	Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : Piano performance support system with a head-mounted display, Proceedings of SPIE, Vol.11794, No.117940O, Online, Jul. 2021. (Summary) 本論文では，VRを用いたピアノ演奏の練習支援手法を提案する．本手法では，演奏者にHMD(ヘッドマウントディスプレイ)を装着してもらい，その画面上に，押すべき鍵盤や指の使い方などを表示して，演奏を導くものである．本手法の有効性を検証するため実験の結果，初心者の演奏スキルを向上させる可能性が確認できた． (Keyword) image processing / pattern recognition / VR (Link to Publication Site) ● Publication site (DOI): 10.1117/12.2589062 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85112478397 (DOI: 10.1117/12.2589062, Elsevier: Scopus)
20.	Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada and Naka Gotoda : Design of a one-on-one training system for basketball players, Proceedings of IIAI-AAI2021, 135-140, Online, Jul. 2021. (Summary) This paper describes the design of a system to developthe feint skill of basketball players in one-on-one situations.When training alone for one-on-one situations, the player lacksan opponent; therefore such training lacks a realistic aspect.The proposed system uses a software to provide a single traineewith an appropriate opponent. To train an offence player, thesystem monitors and analyzes the body movements of an offensiveplayer, providing a counterpart movement with the silhouette ofa visualized defense, whose functions are based on the analysis ofthe monitored offense movement. To train a defense, the system ismodified to provide a realistic offence using a head mount displayworn by a defense trainee. Defense trainee receives feedback afterthe training. (Keyword) Skill Development / One-on-one / Basketball / Sensor (Link to Publication Site) ● Publication site (DOI): 10.1109/IIAI-AAI53430.2021.00024 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85133174599 (DOI: 10.1109/IIAI-AAI53430.2021.00024, Elsevier: Scopus)
21.	ORGIL JARGALSAIKHAN, Stephen Githinji Karungaru and Kenji Terada : Facial emotion recognition using deep learning, Proceedings of IEEJ International Workshop on Sensing, Actuation, Motion Control, and Optimization2020, 1-4, Online, May 2020. (Keyword) image processing / pattern recognition / VR
22.	Stephen Githinji Karungaru, Kenji Matsuura, Hiroki Tanioka, Naoya Kohda, Naka Gotoda and Tomohito Wada : Towards Drone-Video Player Detection and Tracking for Soccer Strategy Analysis, Proceedings of the 6th IEEJ international workshop on Sensing, Actuation, Motion Control, and Optimization, Vol.TT-1, 1-6, Tokyo, Mar. 2020. (Keyword) Human Tracking / Drone / Tiny Objects / Particle Filter
23.	jargalsaikhan Orgil, Stephen Githinji Karungaru and Kenji Terada : Facial emotion recognition using deep learning ls, Proceeding of the 6th IEEJ international workshop on Sensing, Actuation, Motion Control, and Optimization, Vol.TT-11, 1-4, Tokyo, Mar. 2020. (Summary) Emotion recognition has played an important role in the research field of Human Computer Interactions. Therefore, there is need for wellimplemented automatic emotion recognition systems. Nowadays, Neural Networks are one of the best methods to improve emotionrecognition in this field. There are many emotions in wild data available these days. But, many of them are labeled with noise. In this work,firstly, we trained and compared state of the art models such as Resnet, Seresnet and Densenet in FERPlus dataset. After that, we decide thepre-trained model such as LRCN model for emotion recognition in video. (Keyword) pattern recognition / computer vision
24.	Ryosuke Tsuji, Stephen Githinji Karungaru and Kenji Terada : Risky Pedestrian Detection System using In-vehicle Camera, Proceeding of the 6th IEEJ international workshop on Sensing, Actuation, Motion Control, and Optimization, Vol.TT-2, 1-4, Tokyo, Mar. 2020. (Summary) 本稿では車載カメラを用いた危険な歩行者の検出システムを提案する．本手法では，自動車に設置された前方カメラから得られる映像に対して，深層学習を用いることで，歩行者の存在を検出した上で，その人物が走行車に対して危険であるかどうかを判断した上で，ドライバーに警告を与えることが可能である．本手法の有効性を確認するために行なった実験で，高い精度で危険な歩行者のみを検出できることが示唆された． (Keyword) Pedestrian Detection / Tracking / deep learning
25.	MIA MD.MOHSIN, Stephen Githinji Karungaru and Kenji Terada : Tracking Owner of Detected Abandoned Luggage at Public Areas, Proceeding of the 6th IEEJ international workshop on Sensing, Actuation, Motion Control, and Optimization, Vol.P-31, 1-4, Tokyo, Mar. 2020. (Summary) 本論文では，画像処理を用いて放置された手荷物を検出した上で，所有者の追跡する手法を提案する．この手法では公共の場所に設置された監視カメラから得られる映像から学習機能を用いて放置された手荷物を検出し，さらにその所有者を追跡することで，防犯上の問題である公共の場での放置物に対する脅威を取り除くことができる．本手法の有効性を検証する実験で，高い精度で追跡可能であることが示唆された． (Keyword) Abandoned Luggage Detection / Tracking / deep learning
26.	Robert Nsinga, Stephen Githinji Karungaru and Kenji Terada : Mitigating Constraints in Load Balancing and Scheduling in Embedded Systems with Ensemble Models, Proceeding of the 6th IEEJ international workshop on Sensing, Actuation, Motion Control, and Optimization, Vol.TT-3, 1-4, Tokyo, Mar. 2020. (Summary) 本稿では，アンサンブルモデルを用いた負荷分散における制約緩和と組込みシステムにおけるスケジューリング法について提案した．本手法は，複数の予測モデルを組み合わせて最終的な予測結果を出すアンサンブルモデルを用いて，負荷分散における制約の緩和と組込みシステムにおけるスケジューリングを最適化できる．本手法の有効性を確認するためのARMアーキテクチャを用いた実験により，高い性能が実現できることを示した． (Keyword) embedded system / computer vision / アンサンブルモデル
27.	Shu Yano, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Naoya Kohda, Naka Gotoda and Tomohito Wada : Tactics-Trend Analysis for Increasing the Possibility of Shooting in a Basketball Match, Proceedings of IEEE IMCOM2020, 1-4, Taichung, Taiwan, Jan. 2020. (Link to Publication Site) ● Publication site (DOI): 10.1109/IMCOM48794.2020.9001784 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85081137407 (DOI: 10.1109/IMCOM48794.2020.9001784, Elsevier: Scopus)
28.	Stephen Githinji Karungaru : Kitchen Utensils Recognition using Fine Tuning and Transfer Learning, Proceedings of International Conference on Video and Image Processing, 19-22, Shanghai, Dec. 2019. (Keyword) Blind person aid / Transfer learning / Fine Tuning / Wearable sensors (Link to Publication Site) ● Publication site (DOI): 10.1145/3376067.3376104 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85081174634 (DOI: 10.1145/3376067.3376104, Elsevier: Scopus)
29.	Hiroki Tanioka, Kenji Matsuura, Stephen Githinji Karungaru, Naka Gotoda, Kai Tomohiro, Wada Tomohito and Takai Yohei : Player Tracking in Sports Video using 360 Degree Camera, IEEE International Conference on Computational Photography 2019, Tokyo, May 2019.
30.	ZHU Yunpeng, Stephen Githinji Karungaru and Kenji Terada : Human Interaction Recognition Based on Deep Learning, Proceedings of Annual conference on Engineering and Information Technology(ACEAIT2019), 178-186, Kyoto, Mar. 2019. (Summary) 本稿では，深層学習による人のインタラクションの認識手法を提案する．人の動きの認識は動画像処理の分野で注目されているが，近年，深層学習の導入で大きな成果をあげている．本手法では連続フレームにおいて，深層学習を用いることで隠れている時間や空間の問題を解決し，人の動きを認識する．本手法の有効性を検証するためのベンチマークのデータセットを用いた実験により，人の動きを高い精度で認識できることを示した． (Keyword) deep learning / human-computer interaction / pattern recognition
31.	Dongyang Lyu, Stephen Githinji Karungaru and Kenji Terada : Vision-Based Vehicle Recognition Classification Using Convolutional Neural Network and Support Vector Machine, Proceedings of Annual conference on Engineering and Information Technology(ACEAIT2019), 125-132, Kyoto, Mar. 2019. (Summary) 本稿では，改良型のAlexNetを用いた実道路環境下における車両領域抽出と分類手法を提案する．本手法では，車両領域抽出のロバスト性の低さを，高速で軽量化したYOLOを用いて解決し，さらに深層学習とSVMを組み合わせて，SVMで特徴量を正規化することで，モデルの汎化能力を向上させている．本手法の有効性を検証するための実験により，車両検出と車種分類を従来手法よりも高い精度で実行できることを示した． (Keyword) deep learning / image processing / pattern recognition / 自動車
32.	Robert Nsinga and Stephen Githinji Karungaru : Predictive Analysis of Cohesiveness in Multivariate Sequences Using Recurrent Neural Networks, The 166th IASTEM International conference, 1-5, Mar. 2019. (Keyword) Team effectiveness / RNN / Individual ability
33.	Stephen Githinji Karungaru, Kenji Matsuura, Hiroki Tanioka, Tomohito Wada and Naka Gotoda : Ground Sports Strategy Formulation and Assistance Technology Development - Player Data Acquisition from Drone Videos, Proceedings of 8th International Conference on Industrial Technology and Management, 322-326, Mar. 2019. (Summary) Sports analytics aims to provide a competitive advantage to a team or individual in sports by analyzing a collection of relevant statistics. Better strategies in play can be formulated using the information. The core technology necessary for the analysis is the player detection and tracking. Due to limitation of fixed cameras, this work presents a court detection using markers, player detection and tracking using a drone. The method presented is based on perspective transformation, template matching and particle filters. In this work, we can visualize the movement trajectory of a player and extract the real world (on court) player position irrespective of drone height and position. (Keyword) Sports Strategy / Assistance Technology / Drones (Link to Publication Site) ● Publication site (DOI): 10.1109/ICITM.2019.8710735 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85066608325 (DOI: 10.1109/ICITM.2019.8710735, Elsevier: Scopus)
34.	Tomoya Sasaki, Stephen Githinji Karungaru and Kenji Terada : Automatic Recognition of Road Marking using CNN, Proceedings of International Research Conference on Engineering and Technology(IRSET2019), 322-326, Taipei, Jan. 2019. (Summary) 本稿では，深層学習を用いて，路面標識を自動認識する手法を提案した．本手法では，まず自動車の前方に取り付けられた車載カメラにより連続的に撮像された映像から生成される時空間画像から精度良く道路標示領域を抽出した上で，CNNを用いて道路標示を認識し，その結果を音声ガイドと画面表示で運転者に伝えることができる．本手法の有効性を検証する実験で，精度良く路面標識を自動認識できることが示唆された． (Keyword) Road Marking / deep learning / image processing / pattern recognition
35.	Naoya Kohda, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada and Naka Gotoda : Technology-Supported Single Training for One-on-One in Basketball Matches, Proceedings of IEEE TALE2018, 447-453, Wollongong, Australia, Dec. 2018. (Link to Publication Site) ● Publication site (DOI): 10.1109/TALE.2018.8615318 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.1109/TALE.2018.8615318 (DOI: 10.1109/TALE.2018.8615318)
36.	Mobarok Bhuyain, Stephen Githinji Karungaru and Kenji Terada : Robust Detection and Tracking of Moving Objects Using Particle Filter, Proceedings of Annual Conference on Engineering and Applied Science (ACEAT2018), 27-29, Nov. 2018. (Summary) 本稿では，パーティクルフィルタを用いた移動物体の検出と追跡手法を提案した．本手法では，連続して撮像される映像からHOG特徴とSVMを用いて人の領域を抽出し，パーティクルフィルタを用いて人の動きを追跡することで，人同士が重なる混雑時や照明環境の変動にロバストにすることを可能にしている．本手法の有効性を検証する実験により，環境変動にロバストに移動物体の検出と追跡ができることを示した． (Keyword) image processing / pattern recognition / パーティクルフィルタ
37.	Shinya Oshodani, Stephen Githinji Karungaru and Kenji Terada : Traffic volume survey Using Convolutional Neural Network, Proceedings of Annual Conference on Engineering and Applied Science (ACEAT2018), 30-33, Nov. 2018. (Summary) 本稿では，道路監視カメラを用いた深層学習による交通流監視法を提案する．本手法は，道路上方に設置された監視カメラから得られる映像より，車両領域を検出した上で，乗用車，軽自動車，小型貨物車，普通貨物車，バス・大型車のいずれであるかを深層学習により認識し，車種別の交通量を計測することができる．本手法の有効性を検証するために行なった実験により，車種別の交通量を高い精度で計測できることを示した． (Keyword) deep learning / traffic / image processing / pattern recognition
38.	Lin Zong-Yi, Stephen Githinji Karungaru, Kenji Terada and Fang Shin-Pu : Human Action Recognize using SVM, Proceedings of The 5th Annual Conference on Engineering and Information Technology(2018ACEAIT), No.ACEAIT-0174, 547-550, Kyoto, Mar. 2018. (Summary) カメラ映像を用いて，カルマンフィルタとサポートベクターマシーンを用いて人の行動監視をする手法を提案した．本手法では画像処理を用いて人を検出し，さらにカルマンフィルタを用いて追跡することで，人の行動を監視できるものである．これにより歩いている人，ジョギングをする人，走っている人を認識することが可能である．本手法の有効性を検証するために実験をしたところ，約70%の精度で人の行動を認識することができることがわかった． (Keyword) computer vision / image processing / human sensing / カルマンフィルタ
39.	Moriwake Ryo, Stephen Githinji Karungaru and Kenji Terada : Road Sign Character Recognition On a Smart phone using Deep Learning, 4th International Forum on Advanced Technologies, p2-15, Mar. 2018. (Summary) 本論文では，スマートフォンで撮影された画像を用いて，道路標識上の文字を認識する手法を提案した．本システムでは，スマートフォンで道路標識を撮影した画像から文字列を抽出し，ディープラーニングを用いて文字認識することができる．さらに文字認識した情報を用いて，GPSで取得した現在位置とGoogleMapを用いて外国人旅行向けのナビゲーションシステムを構築した．本手法の有効性を検証したところ，約83%の精度で文字認識できることがわかった． (Keyword) Road Sign Characters / CNN / image processing / 文字認識
40.	Yoshino Naoyuki, Stephen Githinji Karungaru and Kenji Terada : Body Physical Parameters Measurement using Kinect, 4th International Forum on Advanced Technologie, p2-14, Mar. 2018. (Summary) 本論文では，RGB-Dカメラを用いて，人の形状を計測するシステムを提案した．本システムは，Kinectを用いて人の3次元形状を取得した上で，被験者の身長，座高，肩幅，股下，全頭高，膝下，股上，頭身，ウエスト，腕の太さ，わたり幅，首の太さなどの人の各部位のサイズを計測することができる．本手法を用いることで服を仮想的に試着することができる．本手法の有効性を検証したところ，各部位のサイズを誤差5cm以内で計測することがわかった． (Keyword) 3DCG / Kinnect
41.	Lkhagvasuren Ulziisaikhan, Stephen Githinji Karungaru and Kenji Terada : Real time backpack detection in visual surveillance based On verticals contour analysis, 6th IIAE International Conference on Industrial Application Engineering 2018, 107-110, Mar. 2018. (Summary) 本論文では，監視カメラから得られる歩行者が持ち歩くバックパックとスリングバッグを画像処理によって検出する手法を提案した．この手法では，人体の内部または近くに発生する垂直線を見つけた上で，いくつかのファジールールを使用して等高線を作成した上でバックパックとスリングバッグを検出することができる．本手法の有効性を検証するたにVIRAT ground video datasetを用いて実験をしたところ，高い精度を得られることがわかった． (Keyword) backpack detection / Visual surveillance / image processing (Link to Publication Site) ● Publication site (DOI): 10.12792/iciae2018.022 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12792/iciae2018.022 (DOI: 10.12792/iciae2018.022)
42.	Nsinga Robert and Stephen Githinji Karungaru : Benchmarking Organizational Performance Dynamics Using Memory Cells Recurrent Neural Networks, 6th IIAE International Conference on Industrial Application Engineering 2018, 9-13, Mar. 2018. (Keyword) Recurrent Neural Networks / Organizational Performance (Link to Publication Site) ● Publication site (DOI): 10.12792/iciae2018.005 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12792/iciae2018.005 (DOI: 10.12792/iciae2018.005)
43.	Stephen Githinji Karungaru and Kenji Terada : Household Items Recognition using Distance Sensor Equipped Video Sunglasses, Risp International Workshop on Nonlinear Circuits, Communications and Signal Processing, 204-207, Mar. 2018. (Summary) 本稿では，目の不自由な人が台所等で作業するために，家庭用品を認識した上で，手にとりやすいように位置を計測する手法を提案する．この手法では，サングラス型カメラから得られる映像を処理することにより道具の種類を認識して，さらにサングラス型カメラに搭載されている距離センサにより位置を推定することが可能である．本手法の有効性を検証する実験で，目の不自由な方の作業の支援が可能であることが示唆された． (Keyword) Video Sunglasses / Distance Sensor / pattern recognition / deep learning / 家庭用品
44.	Kayte J.N., Deshmukh R Ratndeep., Stephen Githinji Karungaru and Kalyankar V. N. : Review of Digital Soil Mapping Procedures, International Journal of Computer Applications proceedings of 2nd ICKE2016, 391-395, Aurangabad, India, Jan. 2018.
45.	P.V. Janse, Ratndeep. R Deshmukh, Stephen Githinji Karungaru, N. V. Kalyankar and Pankaj Koinkar : Hyperspectral Remote Sensing for Agriculture: A Review, International Journal of Computer Applications proceedings of 2nd ICKE2016, 359-363, Aurangabad, India, Jan. 2018.
46.	Sapkal 2)Shubhangi, Deshmukh R Ratndeep., Stephen Githinji Karungaru and Banerjee Soumya : Biometric Cryptosystem for Finger Print Verification, International Journal of Computer Applications proceedings of 2nd ICKE2016, 240-244, Aurangabad, India, Jan. 2018.
47.	Stephen Githinji Karungaru, Kenji Matsuura and Naka Gotoda : Feature Tracking using Particle Filer in Rope Skipping for Gross Motor Skill Development, International Journal of Computer Applications proceedings of 2nd ICKE2016, Vol.1, No.1, 25-29, Aurangabad, India, Jan. 2018.
48.	Kohta Sugawara, Takehiko Yoshikawa, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : A Learning Support System for Integrated Motor Skill by Organized Training Stages, Proceedings of 25Th ICCE, 451-456, Christchurch, NewZealand, Dec. 2017. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85053937284 (Elsevier: Scopus)
49.	Takehiko Yoshikawa, Kohta Sugawara, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Observing the Degree of Distortion in Coordinated Motor Actions, Proceedings of 25Th ICCE, 415-420, Christchurch, NewZealand, Dec. 2017. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85053916064 (Elsevier: Scopus)
50.	Stephen Githinji Karungaru, Kenji Matsuura and Naka Gotoda : Analysis of Rope Skipping Features for Gross Motor Skill Development, International Research Symposium on Engineering and Technology, 97-102, Singapore, Dec. 2017.
51.	Yoshino Naoyuki, Stephen Githinji Karungaru and Kenji Terada : Body Physical Measurement using Kinect for Virtual Dressing Room, Proceedings of the 6th IIAI International Congress on Advanced Applied Informatics( IIAI-AAI 2017), No.SCAI-4, 845-850, Hamamatsu, Jul. 2017. (Summary) 本論文では，3DCGを用いた疑似試着システムを提案した．この手法では，RGB-Dカメラを用いて被験者の3Dデータを取得した上で3Dモデルを作成し，さらに予め作成してある服のデータを用いて，仮想空間上で疑似試着をするものである．3Dモデルでは，身長，首の太さ，腕の太さ，ウエストなどの試着に必要なサイズを取得することで，服のフィット感を3DCGで確認できる．実際にKinectを用いた実験によって，本手法の有効性を確認した． (Keyword) computer vision / image processing
52.	Ryo Moriwake, Stephen Githinji Karungaru and Kenji Terada : Character Recognition in Road Signs using a Smartphone, Proceedings of the 6th IIAI International Congress on Advanced Applied Informatics( IIAI-AAI 2017), 1036-1041, Hamamatsu, Japan, Jul. 2017. (Summary) 本論文では，スマートフォンを用いた道路標識上の文字を認識する手法を提案した．この手法では，スマートフォンで撮影された道路標識に対して，端末上でタップした文字列を認識することができる．本手法では認識にはディープラーニングを用い，さらにGoogle Map APIを適用することで，現在地から目的地までのナビゲーションをすることが可能である．本手法の有効性を検証するために行った実シーンによる実験によって，高精度に文字を認識することがわかった． (Keyword) computer vision / image processing / ディープラーニング (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85040589236 (Elsevier: Scopus)
53.	Hossain Mobarok Bhuyain, Stephen Githinji Karungaru, Kenji Terada and Akinori Tsuji : Real Time Specified Person Tracking in a Crowded Scene using the Particle Filter, Proceedings of the International Conference on Electrical Engineering (ICEE2017), No.SS1-3, 2087-2091, Weihai, China, Jul. 2017. (Summary) 本論文では，パーティクルフィルタを用いて，混雑環境下において，人を追跡する手法を提案した．この手法では，まず取得された映像からHOG特徴とサポートベクターマシーンを用いて人の領域を検出した上で，パーティクルフィルタを適用して人を追跡するものであり，複数の人を追跡することができる．本手法の有効性を検証するために実験を行なったところ，人の検出では約90%，人の追跡では約98%の精度を得ることができた． (Keyword) computer vision / image processing / human sensing
54.	Lkhagvasuren Ulziisaikhan, Stephen Githinji Karungaru and Kenji Terada : Drone Control using Visual Natural Markers, Proceedings of the 2017 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'17), No.3AM2-3-1, 581-584, Guam, Mar. 2017. (Summary) 本論文では，ドローンの自動制御のために，ビジュアルマーカ―を用いたドローン制御手法を提案した．本手法では，ドローンに搭載されているカメラから得らる映像にマーカ検出と追跡に画像処理を適用し，ドローンの安定した自動飛行及び自動着陸等を容易にした．さらに実際にドローンを飛行させて，挙動を自動制御した実験においても，精度の良いマーカの検出と追跡，さらに安定した飛行と着陸が可能であることを確認することができた． (Keyword) computer vision / image processing / ドローン
55.	Stephen Githinji Karungaru, Tomohiro Ishino and Kenji Terada : Safe Driving Support System using Three Onboard Camera, Proceedings of the 2017 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'17), No.3AM1-3-3, 537-540, Guam, Mar. 2017. (Summary) 本論文では，3台の車載カメラを用いて，運転者に危険を知らせ，安全運転を支援するシステムを提案した．この手法では，前方カメラでは車線や歩行者，右折車や右折時の直進車，後方カメラでは車線変更の際の後方走行車等を検知した上で，運転者監視で得られる顔の向きと視線の向きと連動させることで安全運転を支援するものである．実際の車載カメラ映像を用いた実験によって，高精度に危険を検知することが可能であることがわかった． (Keyword) computer vision / image processing / ITS
56.	Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Physical Learning Support using a Smartphone with Image Processing Technologies, Proceedings of ACM IMCOM2017, Beppu, Japan, Jan. 2017. (Link to Publication Site) ● Publication site (DOI): 10.1145/3022227.3022293 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85015246816 (DOI: 10.1145/3022227.3022293, Elsevier: Scopus)
57.	Stephen Githinji Karungaru : Human Action Recognition using Surveillance Cameras and Wearable Sensors, Proceedings of 2nd ICKE2016, Aurangabad, India, Dec. 2016.
58.	Takuya Ishioka, Naka Gotoda, Yuji Kobayashi, Kenji Matsuura, Stephen Githinji Karungaru, Rihito Yaegashi, Toshihiro Hayashi, Kenichi Fujimoto and Hiroshi Murai : Proposal of Organizing Learning Material with Multiple Perceptions Depending on Preference of Physical Training, Proceedings of The Second International Conference on Electronics and Software Science, 56-64, Takamatsu, Japan, Nov. 2016.
59.	Takuya Ishioka, Naka Gotoda, Yuji Kobayashi, Kenji Matsuura, Stephen Githinji Karungaru, Rihito Yaegashi and Toshihiro Hayashi : Proposal of a Methodology based on Organization of Learning Material including Multiple Perceptions for Knowledge Communication of Physical Training, Proceedings of Gong Show & Young Researcher Contributions on ICKM2016, 1-5, Vienna,Austria, Oct. 2016.
60.	Chung Ming-Hsuan, Stephen Githinji Karungaru and Kenji Terada : Intelligent Driver Support Systems: Pedestrian Detection Using HOG Algorithm, Proceedings of the 4th IIAE International Conference on Intelligent Systems and Image Processing, 261-264, Kyoto, Oct. 2016. (Keyword) image processing / サポートベクターマシーン / ITS / HOG (Link to Publication Site) ● Publication site (DOI): 10.12792/icisip2016.047 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.12792/icisip2016.047 (DOI: 10.12792/icisip2016.047)
61.	Lay Kuen-Tsair, Stephen Githinji Karungaru, Chen Yi-Jing and Hsuen Hsing-Chun : Visually Comprehensible QR Codes via Embedding of Big Logos, Proceedings of IEEE International Conference on Signal and Image Processing, 225-230, Beijing China, Oct. 2016. (Link to Publication Site) ● Publication site (DOI): 10.1109/SIPROCESS.2016.7888257 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85018687175 (DOI: 10.1109/SIPROCESS.2016.7888257, Elsevier: Scopus)
62.	Kohta Sugawara, Hiroshi Toyooka, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Development of a Gross Motor Skill by Combining Primitive Motions in Repetitive Exercise, Proceedings of IEEE 5th GCCE, 488-492, Kyoto, Oct. 2016. (Keyword) learning support / combination of primitive motions / feedback (Link to Publication Site) ● Publication site (DOI): 10.1109/GCCE.2016.7800489 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-85010332724 (DOI: 10.1109/GCCE.2016.7800489, Elsevier: Scopus)
63.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : 3-Dimensional Space Modeling using Kinect, Proceedings of the 34th Chinese Control Conference and SICE Annual Conference2015(CCC&SICE2015), No.WeC01-7, Handzhou, China, Jul. 2015. (Summary) 本論文では，RGB-Dカメラから得られるデータを用いて，3次元モデルを生成する手法を提案した．これは特殊な装置を使ったり，厳密なキャリブレーションしたりすることなく取得した3次元データから，回転不変位相限定相関法と位相限定相関法を用いて高精度な3次元モデリングができる手法である．本稿では，さらにいくつかのシーンに対して，Kinectを用いて得られたRGB-Dデータから，高精度に3次元モデルを生成できることを示した． (Keyword) computer vision / image processing / 3-dimensional image processing (Link to Publication Site) ● Publication site (DOI): 10.1109/SICE.2015.7285429 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84960155531 (DOI: 10.1109/SICE.2015.7285429, Elsevier: Scopus)
64.	Stephen Githinji Karungaru : Human Action Recognition using Wearable Sensors and Neural Networks, Proc. of 2015 ASCC Emerging Control Techniques for a Sustainable World, Kota Kitabalu, Jun. 2015. (Summary) Accurate recognition of daily activities could be useful in many fields including health, sports, childcare, and homes for the elderly, etc. In this paper, we propose a human action recognition method using data acquired from wearable sensors and learned using a Neural Network. The data collected from the sensors is processed for features using the Akamatsu transform. The Akamatsu Transform is a signal processing technique that given point, P(i) in a signal, N data points before and after the selected point are used to derive the integral and differential transforms, The Akamatsu Integration is an average of the N data points while the differential is the difference between the integral and the original value. Recently, wearable sensors are emerging as an indispensable method to recognize human actions. (Link to Publication Site) ● Publication site (DOI): 10.1109/ASCC.2015.7244580 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84957678780 (DOI: 10.1109/ASCC.2015.7244580, Elsevier: Scopus)
65.	Nozomi Maitani, Kenji Terada and Stephen Githinji Karungaru : Tire Cracks Detection using Image Processing, Proceedings of the first IEEJ international workshop on Sensing, Actuation, and Motion CONtrol(SAMCON2015), No.TT1-2-3, Nagoya, Mar. 2015. (Summary) 本論文では，画像処理によって黒色のタイヤに存在する黒色のひび割れを検出する手法を提案した．本手法では，まず取得画像に対して，タイヤの円弧方向に極座標変換することによって直行座標画像に変換する．さらにウェーブレット変換を用いて高周波領域に着目して候補領域として抽出した後，輝度や連続性の特徴量によってひび割れであるかを評価する．さらに実際に撮影されたタイヤのひび割れ画像を用いて，本手法の有効性を検証した． (Keyword) computer vision / image processing / 行動認識
66.	Stephen Githinji Karungaru : Feature Extraction from Wearable Sensors for Human Action Recognition, Proc. of 2015 RISP International Workshop on Nonlinear Circuits and Signal Processing, 131-134, KuaLa Lumpur, Mar. 2015. (Summary) Recently, due to the advancement in wireless sensor technology, wearable sensors are emerging as an indispensable method to recognize human actions. In this paper, data collected from such sensor is processed for features using the Akamatsu transform. The features extracted are to be used later to recognize human action using Deep Neural Networks. The Akamatsu Transform is a signal processing technique that given point, P(i) in a signal, N data points before and after the selected point are used to derive the integral and differential transforms, The Akamatsu Integration is an average of the N data points while the differential is the difference between the integral and the original value. Promising features were extracted for action recognition.
67.	Shuhei Koyanagi, Kenji Terada and Stephen Githinji Karungaru : Elderly Monitoring System using Surveillance Cameras, Proceedings of the 2015 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'15), No.1AM1-1-4, Kuala Lumpur, Mar. 2015. (Summary) 本論文では，室内に設置された監視カメラから得られる映像を用いて，行動を解析する手法を提案している．この手法では，高齢者養護施設や高齢者独居住居に設置されたカメラ映像から，主に高齢者の行動を認識するもので，転倒，作業，視聴，運動，休憩，冷蔵庫等の開け閉め，静止，移動などの行動を認識して，もし危険があれば通知することができる．さらに実際に製作した簡易的な部屋における実験によって，本手法の有効性を検証した． (Keyword) computer vision / image processing / 行動認識
68.	Yamazaki Yusaku, Kenji Terada and Stephen Githinji Karungaru : Input Interface using Air Character Recognition, Proceedings of the 2015 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'15), No.28PM2-1-1, Kuala Lumpur, Feb. 2015. (Summary) 本論文では，空中に書かれたAir文字を認識する手法を提案した．本手法は紙やタッチパネルに書かれた文字ではなく，空中に指で書いた文字をカメラ映像によって，その指の動きを追跡することでその文字を認識する手法である．本手法ではカタカナで書かれた文字を認識することが可能だけでなく，消去，リセット，決定などを認識する実用的な手法となっている．さらに実際に空中に書かれた文字を認識する実験で，本手法の有効性を検証した． (Keyword) computer vision / image processing / 行動認識
69.	Junpei Yamamoto, Stephen Githinji Karungaru and Kenji Terada : Road Surface Marking Recognition Using Neural Network, Proceedings of the2014 IEEE/SICE International Symposium on System Integration(SII2014), No.SuA1C.5, 484-489, Tokyo, Dec. 2014. (Summary) In recent years, the number of traffic accidents has rapidly increased. There are various reasons for this, but as one of the most common one is the carelessness of the driver. Therefore, we aim to decrease the number of traffic accidents by automatically recognizing the road signs and informing the driver accordingly. In the proposed method, at first, we use the edge information and after transform it, we can extract the target road area. The road marking candidate is then extracted and recognized using a neural network. (Keyword) computer vision / image processing / ITS / 運転支援 (Link to Publication Site) ● Publication site (DOI): 10.1109/SII.2014.7028087 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84988253874 (DOI: 10.1109/SII.2014.7028087, Elsevier: Scopus)
70.	Masayuki Daikoku, Stephen Githinji Karungaru and Kenji Terada : Indoor Human Action Recognition using Multi Camera, Proceedings of the IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP'14), No.Wed-S1B8-4, Florida, Dec. 2014. (Summary) In this paper, we propose a method for recognition of human actions using multi cameras especially for the detection of suspicious humans. In human region detection, we use background difference and HOG features, with the learning data for HOG made by AdaBoost. We decide whether the detected human is moving or not using the distance of the detected area between frames. We also estimate the direction the human is facing using the width of detection, and finally recognize the standard action using the height measured from the direction. In addition, we recognize suspicious action using duration of detection and presence of abandoned object. Recognition accuracies for walking and stop actions are about 87% , for running action about 54%, for sitting about 96%, for desk working about 83%, and falling about 88%. (Keyword) computer vision / image processing / 行動認識 / 人検出 / HoG (Link to Publication Site) ● Publication site (DOI): 10.1109/CIMSIVP.2014.7013266 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84924228344 (DOI: 10.1109/CIMSIVP.2014.7013266, Elsevier: Scopus)
71.	Stephen Githinji Karungaru, Minoru Fukumi and Kenji Terada : Human Action Recognition using Normalized Cone Histogram Features, Proceedings of the IEEE Symposium Series on Computational Intelligence (CIMSIVP 2014), 12-16, Florida, Dec. 2014. (Summary) In this paper, we propose a normalized cone histogram features method to recognize human actions in video clips. The cone features are extracted based not on the center of gravity as is common, but on the head position of the extracted human region. Initially, the head, hands and legs positions are determined. Thereafter, the distances and orientations between the head and the hands and legs are the extracted and employed as the features. The histogram's x-axis represents the orientations and the y-axis the distances. To make the method invariant to human region sizes, the features are normalized using the L2 normalization technique. The classification method used was the perceptron neural network. We conducted experiments using the ucf-sports-actions database to verify the effective ness of our approach. We achieved an accuracy of about 75% on a selected test set. (Keyword) human sensing / neural network / image processing (Link to Publication Site) ● Publication site (DOI): 10.1109/CIMSIVP.2014.7013265 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84924225195 (DOI: 10.1109/CIMSIVP.2014.7013265, Elsevier: Scopus)
72.	Shang Ke, Stephen Githinji Karungaru, Feng Zuren, Ke Liangjun and Kenji Terada : A GA - ACO Hybrid Algorithm for the Multi - UAV Mission Planning Problem, Proceedings of the 14th International Symposium on Communication s and Information Technologies(ISCIT2014), No.R3-B-3, Incheon, Sep. 2014. (Summary) Multi-UAV mission planning is a combinational optimization problem, that aims at planning a set of paths for UAVs to visit targets in order to collect the maximum surveillance benefits, while satisfying some constraints. In this paper, a genetic algorithm and ant colony optimization hybrid algorithm is proposed to solve the multi-UAV mission planning. The basic idea of the proposed hybrid algorithm is replacing the bad individuals of the GA's population by new individuals constructed by ant colony algorithm. Also, an efficient recombination operator called path relinking is used for mating. A population partition strategy is adopted for improving the evolving efficiency. Experimental results suggested that the proposed hybrid algorithm can solve the test instances effectively in a reasonable time. The comparison study with several existing algorithms shows that the proposed algorithm is competitive and promising. (Keyword) genetic algorithm / アントコロニー / UAV
73.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Vehicle Extraction from Aerial Images Captured using an UAV, Proceedings of the 2014 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'14), 313-316, Honolulu, Hawaii, USA, Mar. 2014.
74.	Masayuki Daikoku, Stephen Githinji Karungaru and Kenji Terada : Human Action Recognition using Multi Cameras, Proceedings of the 2014 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'14), No.3AM2-3-1, 641-644, Honolulu, Mar. 2014. (Summary) Suspicious person must be detected at important sensitive institutions like airports, train stations, sports arenas, etc. to maintain safety at these locations. In this paper, we propose the method for recognition of human actions using multi cameras for detection of suspicious persons. In the process for detecting human, we use background difference and HOG features, leaning data for HOG is made by AdaBoost. We judge whether the detected person is moving or not using the distance of the detection area between frames. We also estimate the direction the person is facing using width of detection, and finally recognize the standard action using attitude measured from the direction. In addition, we recognize suspicious action using duration of detection and presence of left object. Recognition accuracies for walking and stop actions are about 87% , for running action about 54%, and for sitting about 96%. (Keyword) computer vision / image processing / 行動認識
75.	Stephen Githinji Karungaru, Yammoto Jumpei and Kenji Terada : Japanese Road Signs Recognition using Neural Networks, Proceedings of SICE, Dec. 2013. (Summary) Recently, traffic accidents are increasing because of driver's inattentiveness to the road signs. In this work, in order to assist drivers, we propose a recognition system for road signs using neural networks. We first segment road sign regions using color and shape features to get the location information. The initial sign recognition uses template matching. However, since this did not produce satisfactory results, a neural network is used to learn and recognize the signs. A variety of features are considered for training the neural network. The experimental results show that this recognition method is effective for online road sign recognition. (Keyword) 道路標識 / 運転者支援 / neural network / ITS
76.	Stephen Githinji Karungaru, Minoru Fukumi and Kenji Terada : Hand Written Character Recognition using Star-Layered Histogram Features, Proceedings of SICE Annual Conference 2013, Dec. 2013. (Summary) In this paper, we present a character recognition method using features extracted from a star layered histogram and trained using neural networks. After several image preprocessing steps, the character region is extracted. Its contour is then used to determine the center of gravity (COG). This CoG point is used as the origin to create a histogram using equally spaced lines extending from the CoG to the contour. The first point the line touches the character represents the first layer of the histogram. If the line extension has not reached the region boundary, the next hit represents the second layer of the histogram. This process is repeated until the line touches the boundary of the character's region. After normalization, these features are used to train a neural network. This method achieves an accuracy of about 93% using the MNIST database of handwritten digits. (Keyword) 文字認識 / image processing / neural network
77.	Junpei Yamamoto, Stephen Githinji Karungaru and Kenji Terada : Japanese Road Signs Recognition Using Neural Networks, Proceedings of the International conference on Instrumentation, Control, Information Technology and System Integration(SICE Annual Conference 2013), No.MoAT3.3, Nagoya, Sep. 2013. (Summary) Recently, traffic accidents are increasing because of drivers inattentiveness to the road signs. In this work, in order to assist drivers, we propose a recognition system for road signs using neural networks. We first segment road sign regions using color and shape features to get the location information. The initial sign recognition uses template matching. However, since this did not produce satisfactory results, a neural network is used to learn and recognize the signs. A variety of features are considered for training the neural network. The experimental results show that this recognition method is effective for online road sign recognition. (Keyword) computer vision / image processing / 知的システム / signal processing / neural network
78.	Masayuki Daikoku, Stephen Githinji Karungaru and Kenji Terada : Automatic Detection of Suspicious Objects Using Surveillance Cameras, Proceedings of the International conference on Instrumentation, Control, Information Technology and System Integration(SICE Annual Conference 2013), No.MoAT3.6, Nagoya, Sep. 2013. (Summary) Suspicious objects must be detected at important sensitive institutions like airports, train stations, sports arenas, etc. In this paper, we propose a method for automatic detection of suspicious object using a surveillance camera. Person and object areas are extracted using the current frame, previous frame and background. Suspicious object is detected using Histograms of Oriented Gradients (HOG) feature detection method. These features are then learned using the AdaBoost algorithm. Using data collected in our laboratory the system achieved an average accuracy of 85% for 3 types of objects while operating in real time. (Keyword) computer vision / image processing / 知的システム / signal processing
79.	Shang Ke, Stephen Githinji Karungaru, Feng Zuren, Ke Liangjun and Kenji Terada : Periodic Re-optimization based Dynamic Branch and Price Algorithm for Dynamic Multi-UAV Path Planning, Proceedings of the 2013 IEEE International Conference on Mechatronics and Automation(IEEE ICMA2013), No.MP1-6(3), 581-586, Takamatsu, Aug. 2013. (Summary) In this paper, a dynamic branch and price algorithm with a periodic re-optimization framework is proposed to solve the dynamic Multi-UAV path planning problem. By partitioning the planning horizon into a series of time slices, the dynamic problem is transformed into a series of static problems. We then use the adjusted branch and price algorithm to solve each static problem. The prominent characteristic of this algorithm is to improve the solving efficiency at each time slice by succeeding and adjusting the columns from the last time slice. According to the experimental results, the proposed dynamic branch and price algorithm with a periodic re-optimization framework can solve the test instances effectively. (Keyword) UAV / 経路計画 / optimization (Link to Publication Site) ● Publication site (DOI): 10.1109/ICMA.2013.6617981 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84887980666 (DOI: 10.1109/ICMA.2013.6617981, Elsevier: Scopus)
80.	Wang Wei, Stephen Githinji Karungaru, Tsuji Akinori and Kenji Terada : Face Recognition Approach Based on Hyhrid Algorithm, Proceedings of the 2013 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing(NCSP'13), 313-316, Kona, Hawaii, USA, Mar. 2013. (Summary) Face recognition algorithm is a very promising technique in biometric authentication. However, the recognition precision can be affected by many factors, such as feature extraction method and classifier selection. In this paper, a novel algorithm for face recognition is presented. First we detect the face region using an improved AdaBoost algorithm. Second, we extract the appropriate features of the face by wavelet decomposition, and compose the face feature vectors as input to SVM. Third, we train the SVM model by the face feature vectors, and then use the trained SVM model to classify the human face. Finally, we present a face recognition system that can achieve high recognition precision and fast recognition speed in practice. In the training process, three different kernel functions are adopted: Radial basis function, Polynominal and Linear kernel function. Experimental results indicate that the proposed method can achieve recognition precision of 96.78 percent based on 96 persons in Ren-FEdb database.
81.	Wang Wei, Sun Xiangyu, Stephen Githinji Karungaru and Kenji Terada : Face Recognition Algorithm Using Wavelet Decomposition and Support Vector Machines, Proceedings of International Symposuim on OptoMechatronics Technologies(ISOT'12), Paris, Oct. 2012. (Summary) Face recognition algorithm is a very promising technique for biometric authentication. However, the recognition precision can be influenced by many factors. In this paper, a novel algorithm for face recognition is presented according to the advances of wavelet decomposition technique and Support Vector Machines (SVM) model. The extracted features from human images by wavelet decomposition are less sensitive to the facial expression variations. As a classifier, the SVM is provided with high generation performance without a transcendental knowledge. First, we detect the face region from the human face using an improved AdaBoost algorithm. Second, we extract the appropriate features of human face by wavelet decomposition, and compose the extracted features vectors to new feature vectors. Third, we train the SVM model by new face feature vectors, and then use the trained SVM model to classify the human face. In the training process, three different kernel functions are adopted: Linear kernel function, Polynomial kernel function and Radial basis function. Finally, we present a face recognition system that could achieve high recognition precision and fast recognition speed in practice. Experimental results indicate that the proposed method can achieve recognition precision of 96.78 percent based on 96 persons in Ren-FEdb database; from the results, our higher than that by SURF and other approaches. (Keyword) computer vision / image processing / face / AdaBoost / ウェーブレット変換
82.	Ryo Munetsugi, Stephen Githinji Karungaru and Kenji Terada : Building Cracks Detection Using Unmanned Helicopter Images, Proceedings of 8th International Conference on Intelligent Unmanned Systems(ICIUS 2012), No.5A-2, Singapore, Oct. 2012. (Summary) Recently, numerous complicated high rise buildings are being constructed. However, it is difficult to inspect such buildings for structural damage regularly. In this research, we propose a system that can safely inspect such building using images captured by an unmanned helicopter.A panorama image was generated from the consecutive-numbered image acquired from the moving object, and a system which detects cracks in the image was developed. From now on, improvement in the accuracy of crack detection is aimed at. (Keyword) computer vision / image processing / 無人ヘリコプタ / 欠陥検出
83.	Li Qian, Stephen Githinji Karungaru, Kenji Terada and Li Lei : Object Recognition from Aerial Rescue Robots, International Technical Conference on Circuits Systems Computers and Communications, 615-618, Sapporo, Jul. 2012.
84.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Feature Extraction For Human Recognition Based On Bifurcation Points Using Genetic Algorithms, Proc. of NCSP'2012, 615-618, Honolulu, Mar. 2012. (Summary) 本論文では，遺伝的アルゴリズムを用いた分岐点に基づく人物認識のための特徴抽出手法を提案した．画像処理において，人物を認識する手法は様々開発されてきたが，人物はそれぞれ体形が異なり，さらに姿勢も変化するため，精度をあげることが難しい．そこで本手法では，交叉や突然変異などを繰り返しながら最適解を求める遺伝的アルゴリズムを用いることで人物認識のための特徴量を抽出する．
85.	Stephen Githinji Karungaru, Higashidani Takuya and Kenji Terada : Tired State Recognition during Sports using Image Processing, Proc. of NCSP'2012, 643-646, Honolulu, Mar. 2012.
86.	Elmarhomy Ahmed, Stephen Githinji Karungaru and Kenji Terada : A New Approach for Counting Passersby utilizing Space-time Images, ICDIMSP 2012 : International Conference on Digital Image and Multidimensional Signal Processing, Florence, Italy, Feb. 2012. (Summary) Counting people and observing their movements are essential processes for security, organizational administration, and improving corporate business results. This paper presents amethod for automatically counting passersby using virtual-vertical measurement lines. Recognizing a passerby and generating space-time images are processed by animage sequence obtained from a USB camera. Space-time imagery represents recognizable regions surrounding each personwhich are processed fromlabeling-based segmentation. In this study, a space-time image represents the time as pixel-distance which is used to support the algorithm in order to achieve highly accurate counting. Human regions are detected by space colors based on template matching to select the optimal direction and speed. Whether the shape represents only one or two passersby can be ascertained using the relationship between the passerby speed and the human-pixel area. To verify the effectiveness of the proposed method, we performed experiments using a side view camera placed near the entrance. From the experiments, counting and direction accuracy were achieved 97%.
87.	Takahashi Ryo, Stephen Githinji Karungaru and Kenji Terada : Reliable Human Recognition and Authentication using Retina Images, Proceedings of 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2012), 288-292, Yokohama, Feb. 2012. (Summary) In this paper, we proposed a method of authenticating humans using retina images. In this work, we report on the preprocessing required before recognition ins performed. First, we extract only the blood vessel regions from a retina image using the HSV color space. The extracting method is the variable threshold method because of the varying color intensities in the image. After that, several methods including smoothing, sharpening, image composition, labeling and thinning are applied. We achieve about 98% blood vessel extraction rate using 20 retina images. We hope that the resulting image can then be used for feature extraction which can implement human authentication at high recognition rates. (Keyword) image processing / computer vision / human sensing / medical imaging
88.	Wang Wei, Stephen Githinji Karungaru and Kenji Terada : An Eye Location Estimation Algorithm based on HSV Color Space and Template Matching, Proceedings of 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 133-137, Yokohama, Feb. 2012. (Summary) An accurate eyes location method based on skin color using template matching is proposed in this paper. First the H channel in HSV spaces is used to characterize the colors range for skin detection, and roughly locating the face regions. Then an average synthetic eye template is used to locate the eyes. Experimental results indicate that the method based on HSV color space and template matching was proved accurate and fast. It is even unnecessary to do complex pre-processing and extra processing. The proposed method improves the locating speed and accuracy with better robustness. Experimental results also show that the proposed method could correctly locate the eye part in expressionless and in faces various expressions. (Keyword) image processing / computer vision / human sensing
89.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Abandoned Luggage Detection using a Dynamic Background Model and Earth Movers Distance, Proceedings of 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 82-88, Yokohama, Japan, Feb. 2012.
90.	Hemdan Ibrahim, Stephen Githinji Karungaru and Kenji Terada : Robust Facial Features Tracking in Video Sequences using Efficient Template Matching, Proceedings of 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 70-74, Yokohama, Feb. 2012. (Summary) In this paper we proposed the method of detection and tracking of facial features like eyes, nose and mouth in image sequences using efficient template matching. Facial features tracking can improve human-computer interaction and benefit video surveillance. However, this is not a trivial task because of face size and orientation variations etc. This work presents a real time system for detection and tracking of facial features in video sequences. A skin-color model to segment face candidate regions in the image is used. The presence of absence of a face in each region is verified by means of an eye detector, base of an efficient template. Once a face is detected, the pupils, nostrils and lip corners are located and these facial features are tracked in the image sequence. The proposed system is efficient in tracking a mobile person in real time under varying conditions such as illumination, different movement and rotation. (Keyword) image processing / computer vision / human sensing / security
91.	Takayuki Kashihara, Stephen Githinji Karungaru and Kenji Terada : A People Counting Method using Measurement Lines, Proceedings of 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 14-18, Yokohama, Feb. 2012. (Summary) It is important to count the number of people entering or leaving various business premises. This is because by knowing the number of people entering and leaving, strategies to increase sales or ease traffic congestion can easily be formulated. This work proposes extraction of people from a camera, and develops a method of counting them using multiple virtual measurement lines.
92.	Tadahiro Oyama, Higashi Keita, Choge Hillary, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : BCI Based on Single EEG Used Simple Electroencephalograph, Proc. of SICE Annual COnference 2011, 2331-2334, Tokyo, Sep. 2011.
93.	Takuya Shiraishi, Atsushi Ishitani, Momoyo Ito, Stephen Githinji Karungaru and Minoru Fukumi : Operation Improvement of Indoor Robot by Gesture Recognition, Proc. of ICMSAO'2011, 572-575, Kuala Lumpur, Apr. 2011. (Summary) Recently, the demand for the indoor robots has increased. Therefore, increased opportunities for many people to operate the robots have emerged. However, for many people, it is often difficult to operate a robot using the conventional methods like remote control. To solve this problem, we propose a robot operation system using the hand gesture recognition. Our method pays attention to the direction and movement of the hand. We were able to recognize several gestures in real-time. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-79959640449 (Elsevier: Scopus)
94.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Background Updating for Abandoned Luggage Detection at Train Stations, Proc. of ICMLC'2011, Vol.2, 11-14, Singapore, Feb. 2011.
95.	Atsushi Ishitani, Takuya Shiraishi, Stephen Githinji Karungaru, Momoyo Ito and Minoru Fukumi : A Simple Interface for Mobile Robot Using Motion Stereo Vision, Proc. of ICMLC'2011, Vol.2, 174-178, Singapore, Feb. 2011. (Summary) In remote control, user interfaces are very important and it is desired that they have intuitive operability and be simple systems. However, presently, most of interfaces have not satisfied these needs. Therefore, we propose a simple interface to control mobile robots equipped with a camera by instructing it to move to a desired location using the image set to a screen. For the robot to control its movement, it needs to calculate the three-dimensional information of the instructed point. In this work, we calculate the three-dimensional position using motion stereo vision, and perform experiments using a wheeled mobile robot with a single camera in a real environment.
96.	Hitoshi Takano, Stephen Githinji Karungaru, Momoyo Ito and Minoru Fukumi : Stop Sign Recognition from Drive Scenes, Proc. of ICMLC'2011, Vol.1, 549-552, Singapore, Feb. 2011.
97.	Eri Ishikawa, Stephen Githinji Karungaru and Kenji Terada : Gait Features Extraction Method using Image Processing, Proceedings of 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2011), No.P-14, Ulsan, Feb. 2011. (Summary) It is important to observe a person behavior in various scenes using a simple system. Therefore, in this paper, we propose a method to distinguish people by differences of the characteristics of walking.(gait) This method can acquire the characteristic of walker using the head, shoulder, hands and feet. Some experimental results that indicate the effectiveness of the proposed method are also reported. (Keyword) image processing / neural network / human sensing / security
98.	Elmarhomy Ahmed, Stephen Githinji Karungaru and Kenji Terada : A Method for Counting Passersby using Time-Space Image, Proceedings of 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2011), No.P-12, Ulsan, Feb. 2011. (Summary) Recently, there are many serious crimes happening in many institutions and commercial areas. Therefore, security and protection for those areas are needed. This paper proposes an automatic method for counting passersby using horizontal measurement line to solve this serious problem. In this paper, time and direction information are used to count passersby. Therefore, time-space image and measure the speed of each passerby with determination of their distance are applied. In our experiment, the camera is fixed on the front of the hall. A PC is connected to the camera with a frame rate 17 frame per second. Finally, our experimental results prove the effectiveness of our method. (Keyword) image processing / computer vision / human sensing
99.	Jung-Hwa Park, Stephen Githinji Karungaru and Kenji Terada : Recognition of a person's state using FG Vision Sensor, Proceedings of 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2011), No.P-5, Ulsan, Feb. 2011. (Summary) It is effective to observe a person's state while protecting individual's information. FG Vision Sensor is able to acquire three-dimensional information and it can thus offer confidentiality. It is appropriate because the processing speed, when used in a monitoring system, is fast. In this research, we propose to recognize a person's state by using FG vision sensor.Some experimental results that indicate the effectiveness of the proposed method are also reported. (Keyword) image processing / computer vision / human sensing / security / 3-dimensional image processing
100.	Hemdan Ibrahim, Stephen Githinji Karungaru and Kenji Terada : Facial Features-Based Method for Human Tracking, Proceedings of 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2011), No.P-2, 217-222, Ulsan, Feb. 2011. (Summary) The detection and tracking of faces and facial features in video sequences is a fundamental and challenging problem in computer vision. This research area has many applications in face identification systems, model-based coding, gaze detection, human-computer interaction, teleconferencing, etc. This work presents a real time system for detection and tracking of facial features in video sequences. A skin-color model to segment face candidate regions in the image is used. The presence or absence of a face in each region is verified by means of an eye detector, based on an efficient template. Once a face is detected, the pupils, nostrils and lip corners are located and these facial features are tracked in the image sequence. The proposed system is efficient in tracking a mobile person in real time under varying conditions such as illumination, different movement and rotation. (Keyword) image processing / pattern recognition / human sensing / face
101.	Stephen Githinji Karungaru, Kenji Terada and Minoru Fukumi : Improving mobility for blind persons using video sunglasses, Proceedings of 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 1-5, Ulsan, South Korea, Feb. 2011. (Summary) Blind people navigate safely through a familiar room based on strong expectations about the location of objects. If something has been moved, added or removed, it can present a difficulty and potentially a danger. Human eyes are one of the most important body parts that help humans to understand and interact with their surroundings. Most learning and recognition of objects around us is accomplished using the eyes. Given the recent advancement of imagery systems and ever increasing processing power of microprocessors, a machine vision aiding system for the blind can be a reality. In the initial system we propose a system consisting of camera equipped sunglasses to capture the images and pattern recognition to automatically detect Braille tiles to aid mobility of blind persons. The information obtained is passed to the subject using audio messages. (Link to Publication Site) ● Publication site (DOI): 10.1109/FCV.2011.5739729 (Link to Search Site for Scientific Articles) ● Search Scopus @ Elsevier (DOI): 10.1109/FCV.2011.5739729 (DOI: 10.1109/FCV.2011.5739729)
102.	Kazunori Tsuda, Kenji Terada and Stephen Githinji Karungaru : Virtual Darts Using Image Processing, Proceedings of 8th edition of France-Japan and 6th Europe-Asia Congress on Mechatronics, No.Mon2-3, 163-168, Yokohama, Nov. 2010. (Summary) In this paper, we propose a method to realize virtual darts playing using image processing. A dart is composed of various colored parts, including the shaft and flights. Using these color features and extracting the necessary values while the dart is in motion, it is possible to perform trajectory calculations. These trajectory parameters can then be used to simulate virtual darts. Some experimental results that indicate the effectiveness of the proposed method are also reported. (Keyword) image processing / computer vision / human sensing / VR
103.	Toru Seo, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Driver Alcohol Consumption Detection System using EEG, Proceeding of 2010 International Workshop on Nonlinear Circuits, Communication and Signal Processing NCSP'10, 632-635, Honolulu, Mar. 2010.
104.	Kentaro Nakao, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Biped Robot Walking on Uneven Surfaces using Reinforcement Learning, Proceeding of 2010 International Workshop on Nonlinear Circuits, Communication and Signal Processing NCSP'10, 572-575, Honolulu, Mar. 2010. (Summary) Recently, reinforcement learning is one of the approaches focused on to achieve adaptive motion in unknown environment. However, most existing approaches require a large number of trials, which becomes one the major problems when the method is applied to an actual robot. Therefore, in this study, we propose an approach that attains low calculation cost to adapt the robot to unknown environments using reinforcement learning. To increase learning accuracy and efficiency, three patterns of rewards are tried and compared for verification. As a result, 70% success rate walking on small uneven surface was achieved
105.	Atsushi Ishitani, Shiraishi Takuya, Fumitoshi Taoka, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : A Simple Interface for Mobile Robot using Motion Stereo Vision, Proceeding of 2010 International Workshop on Nonlinear Circuits, Communication and Signal Processing NCSP'10, 560-563, Honolulu, Mar. 2010. (Summary) Recently, various kinds of robots are present close to our living environment from their original limited usage in factories, etc. Especially, remote-controlled robots with mobile actuator are being put to practical use for some purposes such as conveying systems, home and office security etc, because the use of remote-controlled robots is easier than autonomous robots. These mobile robots require a controller. In this work, we develop a simple interface for mobile robots. To uses this interface, the users need only point to the position on a screen where they want the robot to move to. After that, the robot controls its own movement between the current position and the target position. To autonomously move to the selected point, the robot needs to calculate the direction and distance of the target from its own position. To calculate direction, we use a simple camera model and pixels surrounding the target point to extract a template. Template Matching is then used to recognize the point during movement. Our interface can forecast movement zone of template image, because it controls movement of the robot. To calculate distance, we use Motion Stereo Vision (MSV). We have two reasons for using this method. First, MSV needs only one camera therefore cost is reduced, and secondly, MSV involves camera movement which is well suited for the mobile robot we are constructing.
106.	Miyoshi Masato, Tadahiro Oyama, Hillary Choge, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Music Classification using Sensitive Words, Proceeding of 2010 International Workshop on Nonlinear Circuits, Communication and Signal Processing NCSP'10, 211-214, Honolulu, Mar. 2010. (Summary) In this paper, we propose an automatic sensitive word score detection method for a music retrieval system. The proposed method consists of two parts, which are a feature extraction part and a score detection part. The score detection part detects a sensitive word score of each music. In this paper, we use an impression represented by 7 levels for the sensitive word score and the Multi-Layer Neural Networks (MLNNs) are used for detector of sensitive word score. Moreover, we investigate the effective features to detect the sensitive word score. To evaluate the proposed method, we conduct a sensitive word score detection experiment.
107.	Fumitoshi Taoka, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Detection of Abandoned Objects from Fluctuating Environment Using Active Background Subtraction, Proc. of IWAIT'2010, No.paper-141, 1-4, Kuala Lumpur, Jan. 2010. (Summary) This paper proposes a new method to detect abandoned objects with a focus on Active Background Subtraction. Some estimate background models for dealing with fluctuating environment are utilized. These models are expressed in the HSV color model for more easily removable shadows and adaptive illumination changes. Using these models for background subtraction the object areas from a background image can be divided. In addition, some edge images that are generated from an input image and the value of difference between background models and the input image are used. This method can fix the object area size and rule out shadows as a candidate for abandoned objects. Finally we make a decision regarding the abandoned objects on the basis of displacement and presence time. Preliminary experiments show that the present method is effective for detecting abandoned objects.
108.	Tadahiro Oyama, Hillary Kipsang Choge, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Improvement Algorithm for Approximate Incremental Learning, Proc. of ICONIP, 520-529, Bangkok(Thailand), Dec. 2009. (Summary) This paper presents an improved algorithm of Incremental Simple-PCA. The Incremental Simple-PCA is a fast incremental learning algorithm based on Simple-PCA. This algorithm need not hold all training samples because it enables update of an eigenvector according to incremental samples. Moreover, this algorithm has an advantage that it can calculate the eigenvector at high-speed because matrix calculation is not needed. However, it had a problem in convergence performance of the eigenvector. Thus, in this paper, we try the improvement of this algorithm from the aspect of convergence performance. We performed computer simulations using UCI datasets to verify the effectiveness of the proposed algorithm. As a result, its availability was confirmed from the standpoint of recognition accuracy and convergence performance of the eigenvector compared with the Incremental Simple-PCA.
109.	Hillary Kipsang Choge, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Palm print Recognition Based on Local DCT Feature Extraction, Proc. of ICONIP, 639-648, Bangkok(Thailand), Dec. 2009. (Summary) In this paper we present a method which extracts features from palmprint images by applying the Discrete Cosine Transform (DCT) on small blocks of the segmented region of interest consisting of the middle palm area. The region is extracted after careful preprocessing to normalize for position and illumination. This method takes advantage of the well known capability of the DCT to represent natural images using only a few coefficients by performing the DCT on each block. After ranking the coefficients by magnitude and selecting only the most prominent, these are then concatenated into a compact feature vector that represents each palmprint. Recognition and verification experiments using the PolyU Palmprint Database show that this is an effective and efficient approach, with a recognition rate above 99 % and Equal Error Rate (EER) of less than 3 %.
110.	Tadahiro Oyama, Choge H.K., Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Wrist EMG Signals Identification using Neural Network, Proc. of IECON 2009, 4322-4326, Porto, Nov. 2009. (Summary) Recently, researches of artificial arms and pointing devices using electromyogram (EMG) have been actively done. However, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist motions using EMG which was measured from the wrist, the range of application will extend furthermore. Moreover, it is predicted that convenience in putting on and taking off the electrode improves. Therefore, we focus on EMG measured from the wrist. In this paper, we aim the construction of wrist EMG recognition system by using fast statistical method and neural network. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-77951574507 (Elsevier: Scopus)
111.	Stephen Githinji Karungaru, Sugizaki Masakazu, Minoru Fukumi, Yasue Mitsukura and Norio Akamatsu : Out-of-Focus Blur Image Restoration using the Akamatsu Transform, Proc. of IECON, 4293-4297, Porto(Portugal), Nov. 2009. (Summary) In this paper, a new image restoration approach using the Akamatsu transform is presented. In the method, by using repeated simple calculations based on the Akamatsu transform, an out-of-focus blurred image can be restored and sharpened. Out of focus is a major problem bothering many people in photography, especially the amateurs. There exits some solution to this problem on both the hardware and software sides. However, none offers a perfect solution. The Akamatsu transform can easily be embedded into hardware to offer faster processing due to its simplicity. Although, initially proposed for speech processing, this paper show the effectiveness of the transform in image processing. The Akamatsu transform is a combination of integral and differential transforms. The algorithm can be effective tools for image restoration in realtime image processing.
112.	Stephen Githinji Karungaru, Sugizaki Masakazu and Minoru Fukumi : Biped Robot Walking Control using Image Processing, Proc. of ICCAS-SICE, 4020-4024, Fukuoka (Japan), Aug. 2009. (Summary) In this paper, a vision system for controlling an autonomous biped robot is presented. Robots need sensors to understand circumstances. There are several types of sensors. Recently, a camera is rapidly becoming the sensor of choice due to the remarkable improvement in computer technology especially in processing power. However, there is the blurred image problem because of camera shake due to robot's walking. Our method focuses on the use of image processing to control a humanoid robot's walking. We fix a camera on a biped robot, and input the images from the camera to PC for processing. The results of the image processing are sent to the robot for control immediately. These real-time image processing and control systems give us an efficient application on future robots. In the initial experiment the objective is to control robot walking upstairs.
113.	Hillary Kipsang Choge, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : A Circle-Based Region-Of-Interest Segmentation Method for Palmprint Recognition, Proc. of ICCAS-SICE, 4993-4997, Fukuoka (Japan), Aug. 2009. (Summary) This paper presents a novel method for optimal region-of-interest (ROI) segmentation for palmprint feature extraction based on the largest inscribed circle. This ensures that the optimal amount of features can be extracted, unlike square-based methods which exclude a substantial area on the outside region of the palmprint image. After position normalization, the middle portion of the palmprint is searched to determine the center from which the largest inscribed circle can be extracted. The circular area is then unwrapped into a fixed-size rectangular strip which is further preprocessed to remove redundancies and then split into seven equal square sub-images. A layered approach is then adopted during the matching stage where each square is successively matched and polled to produce a matching score. Experiments are performed using the `PolyU Palmprint Database' and results show that this is a viable method for palmprint feature extraction, with a recognition rate of above 90% obtained.
114.	Tadahiro Oyama, Hillary Kipsang Choge, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Identification of Wrist EMG Signals using Dry Type Electrodes, Proc. of ICCAS-SICE, 4433-4436, Fukuoka (Japan), Aug. 2009. (Summary) Recently, researches of artificial arms and pointing devices using electromyogram(EMG) have been actively done. However, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist motions using EMG which was measured from the wrist, the range of application will extend furthermore. However, when we use the wrist EMG, there are problems that the individual difference is large and its repeatability is low and so on. In this paper, we aim the construction of wrist EMG recognition system that is robust to these problems.
115.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Improvement of Evolutionary Eye Sensing with Buccal Region",, Proc. of NCSP'2009, 463-466, Honolulu, Mar. 2009.
116.	Toshihiro Yoshida, Takahiro Ogawa, Tadahiro Oyama, Stephen Githinji Karungaru, Yasue Mitsukura, Satoru Tsuge and Minoru Fukumi : Relation Between Mental Change and EEG When Performing Trivial Tasks, Proc. of NCSP'2009, 431-434, Honolulu, Mar. 2009. (Summary) Recently, due to long time usage of computers and Visual Display Terminals (VDTs), mental stress and related illnesses have increased tremendously in today's contemporary society. If a computer based method to diagnose stress becames available, it would go a long way in reducing stress illnesses. Hence, it is thought that quantification of stress is important. In this paper, we study the relationship between stress and electroencephalogram (EEG) signals. We studied the effect of stress (the pysiological parameter) when the brain is doing trivial tasks by measuring the brain waves of a subject before and after doing such a task. We apply principal component analysis (PCA) and linear discriminant analysis (LDA) to characterize the change in each component, extract it and discriminate using a neural network (NN). The trivial task used in this experiment is asking the subject to pick and move beans from one plate to another using chopstick. As a result, it was found that PCA is an effective analysis method in this research. Therefore, it can be said that even trivial task have an effect on the brain that may contribute to stress.
117.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Incremental Learning Method for Biological Signal Identification, Proc. of 13th International Conference on Biomedical Engineering (ICBME2008), Singapore, Dec. 2008. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84891931552 (Elsevier: Scopus)
118.	Nakaura Kazuhiro, Stephen Githinji Karungaru, Takuya Akashi, Yasue Mitsukura and Minoru Fukumi : Fast statistical learning with Kerne-Based Simple-FDA, Proc. of IEEE International Conference on Signal Image Technology and Internet Based Systems, 333-337, Bali (Indonesia), Dec. 2008. (Summary) In this paper, new statistical learning algorithms with kernel function are presented. Recently, iterative learning algorithms for obtaining eigenvectors in the principal component analysis (PCA) have been presented in the field of pattern recognition and neural network. However, the Fisher linear discriminant analysis (FLDA) has been used in many fields, especially face image analysis. The drawback of FLDA is a long computational time based on a large-sized covariance matrix and the issue that the within-class covariance matrix is usually singular. In order to overcome this difficulty, we proposed the feature generation method simple-FLDA which is approximately derived from geometrical interpretation of FLDA. This algorithm is similar to simple-PCA and does not need matrix operation. In this paper, new statistical kernel based learning algorithms are presented. They are extended versions of simple-PCA and simple-FLDA to nonlinear space using the kernel function. Their preliminary simulation results are given for a simple face recognition problem. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-60349108293 (Elsevier: Scopus)
119.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Interactive Interface Using Evolutionary Eye Sensing, Proceedings of the 11th IASTED International Conference Intelligent Systems and Control (ISC 2008), 181-186, Orlando, Florida, USA, Nov. 2008.
120.	Stephen Githinji Karungaru, Fukuda Keiji, Minoru Fukumi and Norio Akamatsu : Classification of Fingerprint Images into Individual Classes Using Neural Networks, Proceedings of the 34th Annual Conference of the IEEE Industrial Electronics Society, 1857-1862, Orlando, Florida, USA, Nov. 2008.
121.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Incremental Algorithm of Discriminant Analysis, Proc. of SCIS&ISIS, 640-643, Nagoya (Japan), Sep. 2008. (Summary) This paper presents a new incremental learning algorithm named Incremental Simple-FLDA. It is the algorithm that improved Simple-FLDA to update an eigenvector by using incremental data. Simpe-FLDA is an approximation algorithm of the linear discriminant analysis where an eigenvector can be calculated by a simple repeated calculation. Using this proposal algorithm, the eigenvector is approximately obtained whenever incremental data is added one by one. We carry out computer simulations on personal authentication that uses face images by incremental learning to verify the effectiveness of this algorithm. As a result, the effectiveness of proposal algorithm is shown.
122.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Incremental Learning Method of Simple-PCA, Proc. of KES'2008, 403-410, Zagreb (Croatia), Sep. 2008. (Summary) n this paper, we propose an incremental learning algorithm named Incremental Simple-PCA. This algorithm is added an incremental learning function to the Simple-PCA that is an approximation algorithm of the principal component analysis where an eigenvector can be calculated by a simple repeated calculation. Using the proposed algorithm, it allows to update faster the eigenvector by using incremental data. To verify the effectiveness of this algorithm, we carry out computer simulations on personal authentication that uses face images and wrist motion discrimination using wrist EMG by incremental learning. As a result, we can confirm the effectiveness from the aspects of accuracy and a computing time by comparing the Incremental PCA that gave the incremental learning function to the conventional PCA. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-57749186836 (Elsevier: Scopus)
123.	Stephen Githinji Karungaru, Minoru Fukumi, Akashi Takuya and Norio Akamatsu : Facial Gesture Simulation for a Single Image using Image Warping, Proceedings of SCIS&ISIS, 631-635, Nagoya, Japan, Sep. 2008.
124.	TADA Ryosuke, Tadahiro Oyama, Satoru Tsuge, Stephen Githinji Karungaru and Minoru Fukumi : Identification of Music According to Singer, Proc. of ICEE'2008, Vol.P-014, 1-5, Okinawa, Jul. 2008. (Summary) We propose a singer identification method using a singer model for retrieving the music data. For the speaker models, we use Gaussian Mixture Models (GMMs) and Vector Quantization (VQ) centroids. To evaluate the proposed method, we conducted the speaker identification experiments. Experimental results show that the correct identification accuracy is 65.0% under the condition that the GMMs are used for the speaker models and the 81.9% under the condition that the VQ centorids are used for the speaker models. We also experimented changing the training data to estimate the best parameter for GMM. The correct identification accuracy is 50.0%, under the condition that training data is 1 and the 95.0%, under the condition that training data is 8. Owing to result of GMM, it has been understood that accurate parameter estimation becomes possible by increasing the number of training data.
125.	YOSHIDA Toshihiro, OGAWA Takahiro, Stephen Githinji Karungaru, Satoru Tsuge, Minoru Fukumi and Yasue Mitsukura : Relation between mental change and EEG when doing Trivial Tasks, Proc. of ICEE'08, Vol.O-160, 1-5, Okinawa, Jul. 2008. (Summary) Recently, due to long time usago of computers and Visual Display Terminals (VDTs), mental stress and related illnesses has increased tremendously in today's contemporary society. If a computer based method to diagnose stress were available it would go a long way in reducing stress illnesses. Hence, it is thought that quantification of stress is important. In this research, we study the relationship between stress and electroencephalogram (EEG) signals. We studied the effect of stress (the pysiological parameter) when the brain is doing trivial tasks by measuring the brain waves of a subject before and after doing such a task. We then apply simple principal component analysis (Simple-PCA) to characterize the change in each component, extract it and discriminate using a Neural Network (NN). The trivial task used in this experiment is asking the subject to pick and move beans from one plate to another using chopstick. A recognition accuracy of about 80 % was achieved.
126.	Miyoko Nakano, Stephen Githinji Karungaru, Satoru Tsuge, Takuya Akashi, Yasue Mitsukura and Minoru Fukumi : Face Information Processing by Fast Statistical Learning Algorithm, Proc. of WCCI'08, 3228-3231, Hong Kong, Jun. 2008. (Summary) In this paper , we propose a new statistical learning algorithm. This study quantitatively verifies the effectiveness of its feature extraction performance for face information processing. Simple-FLDA is an algorithm based on a geometrical analysis of the Fisher linear discriminant analysis. As a high-speed feature extraction method, the present algorithm in this paper is the improved version of Simple-FLDA. First of all, the approximated principal component analysis (learning by Simple-PCA) that uses the mean vector of each class is calculated. Next, in order to adjust within-class variance in each class to 0, the vectors in the class are removed. By this processing, it becomes high-speed feature extraction method than Simple-FLDA. The effectiveness is verified by computer simulations using face images. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-56349105619 (Elsevier: Scopus)
127.	Miyoko Nakano, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Feature Generation for Face Recognition by Fast Statistical Learning Algorithm, Proc. of NCSP08, 84-87, Gold Coast, Mar. 2008. (Summary) In this paper,we proposed a new statistical learning algorithm. This paper quantitatively verifies the effectiveness of the feature extraction performance for face information processing. Simple-FLDA is an algorithm based on a geometrical analysis of the Fisher Linear DIscriminant Analysis. As a high-speed feature extraction method, this algorithm is improved version of Simple-FLDA. First of all, the approximated proncipal component analysis (learing by Simple-PCA) that uses the mean vector of each class is calculated. Next, to adjuast within-class variance in the class to 0, the vectors in the class are removed. By this processing, it becomes hi-speed feature extraction method than Simple-FLDA. The effectiveness is verified by computer simulations using face images.
128.	Kipsang H. Choge, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : Enhancement of Palmprint Images using an Optimized Hexagonal Mulitilayer Perceptron Neural Network, Proc. of NCSP'2008, 423-426, Gold Coast, Mar. 2008. (Summary) The image capture and storage stages of palm and other biometric image applications is susceptible to various forms of noise due to varying lighting conditions and the type of image-input process employed. In this paper, we present a method for improving palmprint image contrast and detail using hexagon-shaped fully connected feedforward neural network with a single hidden layer, similar to the ones that have been used in literature for prediction and regression applications. It is trained, using Outputweight- optimized Back Propagation (OWO-BP), to remove various forms of noise added to the input images, producing an image where the fine details of the principal lines and wrinkles are highlighted. The training is performed using sub-images of the 32x32 pixel gray-scale images of the central palm area. This method offers a viable, fast-learning and one-stop alternative to the application of spatial and spectral image processing techniques such as unsharp masking, spatial filtering and FFT-based sharpening algorithms. The network can also be applied to image restoration problems, if the noisy input image is viewed as a degraded version of the target, enhanced image.
129.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Fast incremental learning algorithm in pattern recognition, Proc. of NCSP'2008, 196-199, Gold Coast, Mar. 2008. (Summary) In a field of pattern recognition, researches on feature extraction and dimension reduction are actively done by using methods of the principal component analysis (PCA) and the linear discriminant analysis (LDA), etc. to data with a lot of attributes. On the other hand, there is an algorithm named Simple- PCA to solve such problems. This is an approximation algorithm of PCA. The algorithm that added the learning function to this Simple-PCA has not been presented yet. In this paper, we propose an Incremental Simple-PCA that added an incremental learning function to the Simple-PCA. Moreover, we carry out the computer simulation on personal authentications that use face images by incremental learning to verify the effectiveness of the proposal algorithm.
130.	Stephen Githinji Karungaru, Minoru Fukumi, Takuya Akashi and Norio Akamatsu : Multiple Faces Detection in Real Time using Neural Networks, Proceedings of the 6th International conference on Computational Intelligent, Man Machine Systems and Cybernetics, 63-68, Canary Islands, Spain, Dec. 2007.
131.	Taro Shibanoki, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Biological Signal Recognition by Fast Statistical Learning Algorithm, Proc. of MJISAT'2007, T2-4-1-T2-4-6, Kuala Lumpur, Nov. 2007. (Summary) This paper presents an improved statistical learning algorithm, which is approximately derived from geometrical interpretation of the Fisher linear discriminant analysis (FLDA). Generally, FLDA has to carry out minimization of a within-class variance. However the inverse matrix of the within-class covariance matrix could not be obtained. In order to overcome this difficulty, a new iterative feature generation method, the simple-FLDA was proposed by authors. In this paper, a further improvement algorithm is introduced into the simple-FLDA and its effectiveness is demonstrated for biological signal recognition problems.
132.	Ai Ikeda, Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Character Recognition of Malaysian Vehicle License Plate by Neural Networks, Proc. of MJISAT'2007, T2-3-1-T2-3-4, Kuala Lumpur, Nov. 2007. (Summary) This paper presents a method to recognize characters of vehicle license plate in Malaysia by using image processing techniques and a neural network (NN). Vehicle license plate recognition is one of important techniques that can be used for the identification of vehicles all over the world. There are many applications such as entrance admission, security, parking control, airport or harbor cargo control, road traffic control, speed control, toll gate automation and so on. In this paper, techniques for a dynamic image analysis including vehicle detection, license plate segmentation, and character extraction are utilized, which include peculiar knowledge on Malaysian license plate. NN is then used for separated character recognition. The training of NN is carried out using features with boundary coding and gradient components. Computer simulations show that character segmentation and recognition can be effectively carried out using the present method.
133.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Construction of Online Tuning System based on Wrist EMG, Proc. of MJISAT'2007, T1-7-1-T1-7-5, Kuala Lumpur, Nov. 2007. (Summary) Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this research, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In the previous research, we proposed a wrist motion recognition system by using Simple-PCA and Simple-FLDA to reduce the number of inputs to a neural network. However, the recognition accuracy was changed considerably by the individual. Therefore, it is thought that the construction of an online tuning system that can consider the individual variation is necessary. In this paper, we propose an improvement algorithm of Simple-PCA named Incremental Simple-PCA that updates eigenvectors sequentially by adding a new data. Moreover, we try the construction of the online tuning system by using this algorithm.
134.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Incremental learning method in wrist EMG recognition system, Proc. of SICE'2007, 2819-2822, Takamatsu, Sep. 2007. (Summary) In a field of pattern recognition, researches of feature extraction and dimension reduction using the Simple-PCA that is an approximation algorithm of the principal component analysis (PCA) are actively conducted. In such a statistical method, a lot of algorithms that perform incremental learning by using new incremental data exist. For example, there is an algorithm named Incremental PCA for PCA. However, the algorithm capable of performing incremental learning to the Simple-PCA has not been presented yet. In this paper, we propose Incremental Simple-PCA that introduces an incremental learning function to the Simple-PCA. Moreover, the effectiveness of this algorithm is verified in EMG pattern recognition.
135.	Minoru Fukumi, Stephen Githinji Karungaru, Satoru Tsuge, Miyoko Nakano, Takuya Akashi and Yasue Mitsukura : Fast Statistical Learning Algorithm for Feature Generatio, Proc. of KES2007, Vol.LNAI 4694, 91-97, Vietri sul Mare, Italy, Sep. 2007. (Summary) This paper presents an improved statistical learning algorithm for feature generation in pattern recognition and signal processing. It is approximately derived from geometrical interpretation of the Fisher linear discriminant analysis (FLDA). Recently FLDA has been often used in many fields, especially face image recognition. The drawback of FLDA is a long computational time based on a large-sized covariance matrix and the issue that the within-class covariance matrix is usually singular. In order to overcome the difficulty of FLDA, a new iterative feature generation method, the simple-FLDA was proposed by authors. In this paper, further improvement is introduced into the simple-FLDA and its effectiveness is demonstrated for preliminary personal identification problem. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-38049107774 (Elsevier: Scopus)
136.	Tadahiro Oyama, Yuji Matsumura, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Discrimination of Wrist EMG Signals using a Statistical Method, Proc. of 2007 RISP International Workshop on Nonlinear Circuits and Signal Processing, 393-396, Shanghai, Mar. 2007. (Summary) In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In the previous study, the recognition accuracy was changed considerably by the individual. Therefore, we thought that the construction of an online tuning system that can consider the individual variation was necessary. In this paper, we propose an improvement algorithm of Simple-PCA that changes eigenvectors sequentially by adding data. Moreover, the construction of the online tuning system is carried out by using this algorithm.
137.	Kou Nakamichi, Stephen Githinji Karungaru, Minoru Fukumi, Takuya Akashi, Yasue Mitsukura and Motokatsu Yasutomo : Extraction of the Liver Tumor in CT Images by Real-coded Genetic Algorithm, Proc. of IASTED CI'2006, 366-371, San Francisco, Nov. 2006. (Summary) The purpose of this work is the construction of an automatic diagnosis support system for CT images in order to reduce the doctor's load. Toward this end, in this paper, a method to extract liver tumors in CT images using a real-coded genetic algorithm is proposed. Conventionally, a threshold is necessary to extract an object from an image. However, such a method is not effective for CT images because gray scale values are different in each image. Therefore, in this paper, we propose the method for extracting the tumor in the liver from the CT image without the need of a threshold. In this method, a polygon enclosure of the liver tumor is extracted using a GA.
138.	Takenaka Yusuke, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Isolated Syllable Recognition on Mobile Terminal Devices, Proc. of IASTED International Conference on Computational Intelligence, 366-371, San Francisco, Nov. 2006. (Summary) The aim of this work is the establishment of isolated syllable recognition for Japanese language on mobile terminal devices and/or the retry after the failure in speech recognition. The subjects in this study are five Japanese vowels. The experiment was carried out on 100 sets of five Japanese vowels from four men. The experiment for recognition was carried out using the Akamatsu transform. The experiment demonstrated the effectiveness of the proposed technique for recognizing the isolated 100 sets. This paper serves as an introduction on the use of the Akamatsu transform in speech recognition and does not, as yet, compare the results with existing methods.
139.	Tadahiro Oyama, Yuji Matsumura, Stephen Githinji Karungaru, Yasue Mitsukura and Minoru Fukumi : Recognition of Wrist Motion Pattern by EMG, Proc. of SICE-ICCAS'2006, 599-603, Busan, Oct. 2006. (Summary) Recently, studies of artificial arms and pointing devices using ElectroMyoGram (EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application can extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using simple-PCA and simple-FLDA to reduce the number of inputs to NN. It was confirmed that the present approach was one of the techniques which were effective in the wrist recognition experiment.
140.	Stephen Githinji Karungaru, Minoru Fukumi, Akashi Takuya and Norio Akamatsu : A Simple 3D Edge Template for Pose Invariant Face Detection, Proc. of Knowledge-Based & Intelligent Information & Engineering Systems (KES), 692-698, Bournemouth, Oct. 2006.
141.	Morioka Yoshiyuki, Stephen Githinji Karungaru, Yasue Mitsukura, Minoru Fukumi and Norio Akamatsu : Automatic Extraction of Heart Contour using SNAKES, Proc. of SICE-ICCAS 2006, 1477-1480, Busan, Oct. 2006. (Summary) Recently, as sophisticated medical instruments have been developed, the internal state of a human body has become well-known. In particular, in the examination of heart, non-surgical and non-intrusion ultrasonic diagnostics are generally utilized. However, the diagnosis depends on the doctor's subjectivity and experience. Furthermore, the doctor's burden increases because the contour of the heart is extracted by manual operations. Therefore, the development of a system that offers objective information in addition to a subjective judgment of the doctor by extracting and analyzing quantitative information from image analysis by computers is necessary. In this paper, the contour of the chamber wall is extracted by using an active contour model SNAKES as a preprocessing of the heart disease detection. The contour has been extracted by using SNAKES of the expansion model from the inner surface of heart
142.	Ogawa Takahiro, Stephen Githinji Karungaru, Yasue Mitsukura, Minoru Fukumi and Norio Akamatsu : Feature Extraction in Listening to the Music Using Statistical Analysis of the EEG, Proc. of SICE-ICCAS 2006, 5120-5123, Busan, Oct. 2006. (Summary) In order to solve stress problems, researchers have studied healing, especially the music therapy. It is mentioned that objective evaluation of the music therapy is an important assignment, and some researchers have tried objective measurement based on physiological change. In this paper, the purpose is extraction of features that may be influenced by the music. We pay attention to EEG (electroencephalogram) as an objective and absolute scale. This paper proposes a method that extracts features of the EEG by the CDA (canonical discriminant analysis). From the result of the experiment, it is suggested that the CDA extracts the features influenced by the individual and the music type
143.	Watanabe Takumi, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Design of an IR Communication Link for a Computer-Controlled Humanoid Robot, Proc. of SICE-ICCAS 2006, 3496-3499, Busan, Oct. 2006. (Summary) Recently, many humanoid robots can be formed on television programs and public events. In this paper, we pay attention to such robots. Under this background, diverse parts have been developed and many symposiums have been held to share domain knowledge with many engineers. Furthermore, as for the robot technology, we think that a robot which makes humanlike movement and general view has been developed. However, if a multifunction robot were developed, it could work instead of a human and our lifes could be more convenient and less risky. However autonomous action is very difficult to achieve because a robot cannot recognize varying environment all of the time. In this paper, we focus on how to recognize such environments. The environment is recognized using a camera and is learned with a neural network (NN). The autonomous action can be learned by the NN on the robot or transferred from a PC after action learning. In this work, we use the latter method, and then transmit the image that is necessary to control the robot from a PC because the robot cannot acquire the image by itself.
144.	Takahashi Yasuyuki, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Feature Point Extraction in Face Image by Neural Network, Proc. of SICE-ICCAS 2006, 3783-3786, Busan, Oct. 2006. (Summary) Conventionally, manual operations that specify positions of feature points such as eyes and nose are needed when morphing is carried out for a face image. In this work, the feature points are therefore extracted by using face area detection and a feature points decision methods to automate positional specification of feature points. As a result, the morphing of a face image can be carried out without manually specifying feature points. Face area detection is achieved by a threshold method using the YIQ color system. Feature points decision method extracts feature points by using a 3 layer perceptron type neural network (back-propagation). The attribute of the feature of eyes is defined to be a value of A in the color system LAB. In the same way, the attribute of feature points of the lip is defined as a value of B in the color system LAB. The extraction experiment of feature points was conducted from 120 face images by using the neural network, and the effectiveness of the present method was verified.
145.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Downsized Genetic Algorithm by Automatic Search Domain Control for Lips Detection, Proc. of the International Conference on Soft Computing and Intelligent Systems and International Symposium on advanced Intelligent Systems (SCIS & ISIS 2006), 1312-1317, Tokyo, Sep. 2006. (Summary) In this paper, a method of downsizing a genetic algorithm (GA) for lips detection is described. As part of the objectives, we also try to acquire information to represent the lips. GA is very useful for optimization of parameters in complex image matching. When GA is applied to the real-time processing, the search speed is a issue with keeping the accuracy. Using small population is one of the approaches to improve the GA search speed. However, this can cause the low accuracy, because diversity of the population will be lost. In order to avoid this problem, we propose a downsized GA with automatic search domain control. In this paper, the optimization problem is template matching. The target image includes a face of talking person and has significant changes of a whole scene by camera motion. The template image is only one closed mouth and prepared for each environment and person, because of personal use. In simulations, a simple image is used, which is the basis of video sequence. Our proposed method is verified by comparison of a process of evolution between a downsized GA and a standard GA.
146.	Fukuda Keiji, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Personal Authentication using Fingerprints, Proc. of the International Conference on Soft Computing and Intelligent Systems and International Symposium on advanced Intelligent Systems, 1144-1149, Tokyo, Sep. 2006.
147.	Takizawa Atsushi, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Recognizing Parked Vehicles License Plate Using Image Frame-Difference and Template Matching, Proc. of the International Conference on Soft Computing and Intelligent Systems and International Symposium on advanced Intelligent Systems, 141-144, Tokyo, Sep. 2006. (Summary) In this paper, parked vehicles license plate recognition using image frame-difference and template matching is proposed. Image frame-difference is used to extract the vehicle area, reducing the license plate search domain, thereby reducing the total search time. The processes of expansion and reduction are then applied to reduce the noise in the extracted plate domain. Based on the data from 83 vehicles, the most likely plate area is then decided. License plate recognition is carried out using template matching. For each possible character, three templates are prepared. We then performed computer simulations to show the effectiveness of our method. From the result, it was confirmed that the preprocessing method was effective.
148.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru and Minoru Fukumi : Eye Detection and Tracking using Genetic Algorithm, Proceeding of the 4th International Conference on Computing, Communications and Control Technologies, 26-31, Orlando, Jul. 2006.
149.	Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Akashi Takuya : Optimizing Feature Extraction for the Camera Mouse using Genetic Algorithms, WSEAS Proceeding on Computers, 873-877, Jul. 2006.
150.	Tadahiro Oyama, Yuji Matsumura, Stephen Githinji Karungaru, Yasue Mitsukura and Minoru Fukumi : Construction of Wrist Motion recognition System, Proc. of 2006 RISP International Workshop on Nonlinear Circuits and Signal Processing, 385-388, Honolulu, Mar. 2006. (Summary) Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using Simple-PCA and Simple-FLDA to reduce the number of inputs to NN. It was confirmed that it was one of the techniques which were effective in the wrist recognition experiment.
151.	Takuya Akashi, Yuji Wakasa, Kanya Tanaka, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Genetic Eye Detection System, Proc. of 2006 RISP International Workshop on Nonlinear Circuits and Signal Processing, 377-380, Honolulu, Mar. 2006. (Summary) In this paper, high-speed size and orientation invariant eye tracking in an active scene using template matching and genetic algorithms is proposed. As part of the objectives, we also try to acquire numerical parameters to represent the eye, for example, position, scaling, and rotation angle. The information is useful for many applications, where high performance is required, such as eye gaze detection or estimation for robot perception and mobile devices interfaces. The difficulty in eye tracking is mainly due to motion of the human head and the active scene by free camera motion. Our proposed system is based on template matching using genetic algorithms (GAs). Only one artificial template is used for every human user. Various geometric changes of iris can be supported by genetic algorithms. In this paper, eye tracking system with genetic algorithms is proposed, and selection of the best template image is described. We achieved a eye detection accuracy of 74 % at an average processing time of 0.03 seconds.
152.	Michiyo Nishioka, Yasue Mitsukura, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Measurement of Skin Texture Using Artificial Neural Network and SOM, Proc. of 2006 RISP International Workshop on Nonlinear Circuits and Signal Processing, 33-36, Honolulu, Mar. 2006. (Summary) In this paper, the purpose is to offer a different diagnostic method for skin texture evaluation using sophisticated skin diagnostic system that a layperson can easily use at home. The experiments for evaluation were carried out using an artificial neural network (NN) and a Self-Organizing Map (SOM) to measure the degree of similarity. The Fast Fourier Transform (FFT) was performed to skin images and the number of skin textures counted used as the input data. Then we use Simple Principal Component Analysis (SPCA) in order for PCA to achieve high speed processing. In this experiment, we use newly SPCA and could obtain effective result comparison with before. Moreover, the mapping images of SOM and SPCA were obtained the result that is nearby positioned the similar image of skin.
153.	Stephen Githinji Karungaru, Youngmin Choie, Minoru Fukumi and Norio Akamatsu : Korean Lightweight Font Development using Outline Compression Reduction Function, Proc. of The 12th Korea-Japan Joint Workshop on Frontiers of Computer Vision, 289-294, Tokushima, Feb. 2006.
154.	Yoshiki Kubota, Yasue Mitsukura, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Automatic Extraction System of a Kidney Region from CT Images, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T7-3, 1-5, Kuala Lumpur, Dec. 2005. (Summary) In this paper, a kidney region extraction method as a preprocessing of kidney disease detection is proposed. The kidney region is detected based on its contour information that is extracted from a CT image using a dynamic gray scale value refinement method based on the Q-learning. An initial point to extract the kidney contour is decided by training gray scale values along horizontal direction using a Neural Network (NN). Furthermore the kidney contour is corrected by using SNAKES. It is demonstrated that the proposed method can accurately detect the kidney contour from CT images of any patient.
155.	Takahiro Ogawa, Yasue Mitsukura, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Relevance of the EEG and feeling during listening to the music, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T7-5, 1-5, Kuala Lumpur, Dec. 2005. (Summary) In order to solve stress problems, researchers have studied music therapy. In this paper, the purpose is extraction of features that may be influenced by the music. We pay attention to EEG (electroencephalogram) as an objective and absolute scale. This paper proposes a method that extracts features of the EEG by PCA (principal component analysis) and CDA (canonical discriminant analysis). Then we analyze each feature data by NN (neural network). In order to examine whether the proposal system is effective, we try computer simulations for the EEG classification. According to recognition rate by the NN, it was considered that the CDA extracted and classified the features of the EEG better than the PCA.
156.	Ryohei Haga, Yasue Mitsukura, Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Motokatsu Yasutomo : Automatic Extraction of Left Ventricle by Using X-Ray Photogram, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T2-3, 1-5, Kuala Lumpur, Dec. 2005. (Summary) Recently, as sophisticated medical instruments are being developed, the inside state of a human body has become well known. However, doctor's burden becomes heavier because the number of images that are taken with medical instruments per person drastically increases. In such cases, the development of automatic extraction system for the organs is needed. In this paper, we propose the extraction the left ventricle in such images using the Gabor transform and SNAKES. The kind of image processed in this work is the X-ray photograms of the left ventricle by cardiac catheterization.
157.	Yoshiyuki Morioka, Yasue Mitsukura, Stephen Githinji Karungaru, Minoru Fukumi, Norio Akamatsu and Motokatsu Yasutomo : Contour Extraction of Heart from Ultrasonic Image Using SNAKES, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T7-3, 1-4, Kuala Lumpur, Dec. 2005. (Summary) Recently, as sophisticated medical instruments have been developed, the inside state of a human body has become well-known. In particular, in the examination of heart, non-surgical and non-intrusion ultrasonic diagnostics are generally utilized. However, the diagnosis, depends on the doctor's subjectivity and experience. Furthermore, the doctor's burden increases because the contours of the heart are extracted by manual operations. Therefore, the development of automatic diagnostic imaging systems is needed. In this paper, the contour of the entire heart and left ventricle is extracted by using an active contour model SNAKES as a preprocessing of the heart disease detection. The entire heart contour made with SNAKES is used as a control point in the next image to automate contour tracking.
158.	Yuji Matsumura, Minoru Fukumi and Stephen Githinji Karungaru : Wrist Motion Recognition System by Neural Networks, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T6-3, 1-6, Kuala Lumpur, Dec. 2005. (Summary) We propose a recognition system based on wrist movements by focusing on ElectroMyoGram (EMG), that is, the living body signal generated with voluntary movement of subject muscles as the initial stage for construction of the total operation device. In this paper, we aim for construction of a high-speed and high-accurate EMG recognition system using Fast Fourier Transform (FFT) for feature extraction, Simple-PCA (SPCA) for feature compression, and Neural Networks (NN) for recognition. Furthermore, we select evaluation data using Self-Organizing Map (SOM) for recognition accuracy improvement. From results of computer simulation, it is shown that our approach is effective in the improvement of recognition accuracy.
159.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : License Plate Localization Using Template Matching, CD Proc. of 9th International Conference on Mechtornics Technology, Vol.1, No.T4-3, 1-5, Kuala lumpur, Dec. 2005.
160.	Minoru Fukumi, Stephen Githinji Karungaru and Yasue Mitsukura : Feature Generation by Simple-FLDA for Pattern Recognition, Proc. of International Conference on Computational Intelligence for Modelling, Control and Automation, Vol.1, No.2, 730-734, Wien, Nov. 2005. (Summary) In this paper, a new feature generation method for pattern recognition is proposed, which is approximately derived from geometrical interpretation of the Fisher linear discriminant analysis (FLDA). Recently the FLDA has been used in many fields, especially face image analysis. The drawback of FLDA is a long computational time based on a large-sized covariance matrix and the issue that the within-class covariance matrix is usually singular. Generally FLDA has to carry out minimization of a within-class variance. However in this case the inverse matrix of the within-class covariance matrix cannot be obtained, since data dimension is generally higher than the number of data and then it includes many zero eigenvalues. In order to overcome this difficulty, a new iterative feature generation method, a simple FLDA is introduced and its effectiveness is demonstrated for pattern recognition problems.
161.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Malaysian License Plate Recognition Using Artificial Neural Networks and Evolutionally Computation, Proc. of International Federation for Systems Research, Vol.1, No.S3-7-3, 1-5, Kobe, Nov. 2005.
162.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Automatic Facial Gesture Construction Using Image Warping, Proc. of International Federation for Systems Research, Vol.1, No.S3-2-2, 1-6, Kobe, Nov. 2005.
163.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Face Gesture Recognition Using Artificial Neural Networks, Proc. of The Society of Instrument and Control Engineers (SICE) Annual Conference, 136-140, Okayama, Aug. 2005.
164.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Face Detection: Size and Rotation Invariance using Genetic Algorithms, Proc. of 2005 RISP International Workshop on Nonlinear Circuits and Signal Processing, 211-214, Honolulu, Mar. 2005. (Summary) 本国際会議論文は，カラー画像中から顔を高速高精度に検出する方法を提案している．特に本方法では，色情報に基づいてYIQ成分の閾値をを用いて顔候補領域を推定し，その後ニューラルネットワークにより顔候補の洗練化を行う．顔判定用のニューラルネットワークは速度を改善するために結合数を低減化させる工夫を行っている．さらに，遺伝的アルゴリズムを用いて，顔のスケール変化，回転に不変な構造を導入して様々な顔を検出できるようにしている．計算機シミュレーションの結果から，本手法の有効性を定量的に検証している．
165.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Automatic Face Metamorphosis in Color Images, Proc. of 2005 RISP International Workshop on Nonlinear Circuits and Signal Processing, 131-134, Honolulu, Mar. 2005. (Summary) 本国際会議論文では，カラー顔画像のモーフィングを行うための方法を提案している．特に，顔の制御点(特徴点)を自動的に抽出する方法を考案している．この方法ではエッジ画像を作成し，スムージングを行った後に，エッジ画像の集中具合に基づいて自動的に顔の特徴点(鼻，目の中心，口の両端)を5点抽出している．この制御点に基づいて，ワーピングと色情報の変換に基づいてモーフィングを行う方法である．計算機シミュレーションにより，本手法の有効性を確かめている．
166.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Face Recognition using Genetic Algorithm based Template Matching, Proc. of IEEE International Symposium on Communications and Information Technologies'2004, 1252-1257, Sapporo, Oct. 2004. (Summary) 本国際会議論文は，遺伝的アルゴリズムにより顔検出を効率的に行う方法を提案している．本手法では，テンプレートを2種類(カラーとエッジ画像)用意し，かつ顔の特徴点だけを含むT字型のテンプレートを提案し，使用している．様々な顔画像に対する計算機シミュレーションにより，従来法よりも優れた顔検出精度が得られることを定量的に検証している． (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-21844448123 (Elsevier: Scopus)
167.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Feature Extraction for Face Detection and Recognition., Proc. of 13th IEEE International Workshop on Robot and Human Interactive Communication'2004, No.pp. 235-239, Kurashiki, Japan, Sep. 2004. (Summary) We propose a facial feature extraction method for face detection and recognition using image segmentation with adaptive thresholds and real coded genetic algorithm guided shape matching. The shapes template is constructed using the average outer edges of the lips and the eyes. Image segmentation is performed using a region growing method, whose seeds are determined using a hybrid method that combines histogram, random and pixel-by-pixel methods. Adaptive thresholds are calculated using color variance. Color spaces used are the YIQ, XYZ and the HIS. Color variance is worked out using square, star and plus kernels. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-20444465211 (Elsevier: Scopus)
168.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Recognizing Frontal Faces using Neural Networks., Proc. of 8th International Conference on Knowledge-Based Intelligent Information & Engineering Systems'2004, 1045-1050, Wellington, Sep. 2004. (Summary) In this paper, a neural network based face recognition system is presented. One of the main problems encountered when using neural networks for face recognition is luck of enough training data. This is because, in most cases, only one image per subject is available. Therefore, one of our objectives is to solve the problem of luck of enough data to train neural networks. For each image we ''increase'' the data available by several processes for example, mirroring of the image, using color, edges information, etc. The neural network is trained using structural learning to reduce its size. To represent the face color, the YIQ and the XYZ color spaces are used.
169.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Morphing Face Images Using Automatically Specified Features, Proc. of Midwest Symposium'2003, 995-1000, Cairo, Dec. 2003. (Summary) In this paper, we present a method using which face images can be automatically warped and morphed. Image warping can be defined as a method for deforming a digital image to different shapes. Image morphing combines image warping with a method that controls the color transition in the intermediate images produced. To morph one image to another, new positions and color transition rates for the pixels in each of the images in the sequence must be calculated. Three processes are involved; feature specification, warp generation and transition control.
170.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Reconstruction of Facial Skin Color in Color Images, Proc. of Knowledge-Based Intelligent Information & Engineering Systems'2003, 1135-1141, Oxford, Sep. 2003. (Summary) In this paper, a method to recover and reconstruct skin color from images over or under-exposed to scene illumination is proposed. The skin color regions most susceptible to over-exposure include areas around the forehead, tip of the nose and the cheeks. This method uses a feed-forward neural network and a distance measure method to learn and construct the skin color face image map. The color distance measure method used is the Cylindrical Metric method (CMM). The relationships between neighboring pixels skin color distance and their relative position in a face are learned using the neural network. This information is then used to reconstruct over or under-exposed skin color regions.
171.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Neural Networks and Genetic Algorithms for Learning the Scene Illumination in Color Images, Proc. of IEEE International Symposium on Computational Intelliegnce in Robotics and Automation, 1085-1089, Kobe, Jul. 2003. (Summary) This paper proposes the use of neural networks to estimate the scene or camera white balancing illuminant in color images. A real coded genetic algorithm is also used to shirk the size of the neural network input data (thus, a smaller network that will train and run faster), and to identify the areas of a scene that contain the most information about, and therefore best represent the scene illuminant (this offers better data quality thereby improving the accuracy). In addition structural learning with knowledge was incorporated with the back propagation method to further reduce the size of the neural network. The final appearance of the colors in an image depends on many factors. The three main factors are the scene illumination, the illuminant used to white balance the image acquisition device and the properties of the object. While both the camera white balancing illuminant and the properties of the object might be known a prior, it is not always possible to control the scene illumination. In this paper, facial skin color was used as the object interest. Given a visual scene, the proposed method first searches for the presence of at least one face in the scene. If one is found, the genetic algorithm is used to extract the inputs to the neural network, that in turn outputs the estimated scene illuminant. Presently, the proposed method is used to estimated four illuminants in the range 2300K to 6500K. (Link to Publication Site) ● Publication site (DOI): 10.1109/CIRA.2003.1222148 (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84856552075 (DOI: 10.1109/CIRA.2003.1222148, Elsevier: Scopus)
172.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Identifying Scene Illumination using Genetic Algorithms and Neural Networks, CD-ROM Proc. of 2002 International Conference on Neural Information Processing, 1-5, Singapore, Nov. 2002. (Summary) The scene illumination that is present when an image is captured plays a major role in the appearance of the colors of the objects in that image. This is because color is not a physical property of objects and therefore, it is not constant under most conditions, for example, changing scene illumination. We target skin color as the object of interest in an image. We used neural networks to learn and identify which of four different types of scene illuminations were present in a given scene. A real coded genetic algorithm was also used to shrink the size of the neural network input data, and to identify the areas of a scene that contain the most information about, and best represent the scene illuminant Once a scene illuminant can be identified, it can go a long way in helping to correct and normalize skin color in systems' that are sensitive to skin color changes, for example face detection and recognition. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-84964546760 (Elsevier: Scopus)
173.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Estimating Scene and Camera calibration Illuminants in color images, Proc. of SIP, 266-270, Kuai, Hawaii, Aug. 2002. (Summary) 本国際会議論文は，ニューラルネットワークにより，過露光や露光不足の状態の顔画像に対する肌色部分を補正する方法を提案している．特に，肌色と色温度との関係を解析的に調べ，ニューラルネットワークの学習機能により補正している．カラー顔画像に対する計算機シミュレーションにより，本手法の有効性を定量的に検証している．
174.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Skin Color Compensation Under Varying Scene Illumination, Proc. of IASTED International Conference on Artificial Intelligence and Soft Computing, 500-505, Banff, Jul. 2002. (Summary) We propose to normalize skin color under varying illumination using a graphical method under any type of scene illumination. Under a given illumination, skin color occupies a well-defined region in certain color systems like YIQ, YCrCb etc and therefore can be easily detected using threshold techniques. When a scene illuminant changes, the skin color changes to a different color, but the skin color can still be detected if the threshold were adjusted. This information can be mapped and used to compensate for skin color changes under any illuminant.
175.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Rotational Invariant Human Faces Detection in Color Images, Proc. 20th IASTED Int. Multi-Conf. on Applied Informatics (AI2002), 78-83, Innsbruck, Feb. 2002. (Summary) This paper presents a skin color filter based detection method that can detect faces in one of the three possible orientations. Since skin color is rotational invariant, we propose the use of a Skin-color Edge Angular Measurement (SEAM) method. This method finds the edges of the skin color and then uses the least square (LS) method to draw straight-line segments along the edges. After pairing the line segments, the angle each of them makes with the horizontal plane is then calculated. Using this calculation, it is possible to determine the direction of orientation of the faces, re-rotate them to a frontal pose and then perform face detection. This filter is fast, with a detection accuracy of 75.8% on our test set.
176.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Detection of Human Faces in Visual Scenes, Proc. of Seventh Australian and New Zealand Intelligent Information Systems Conference, 165-170, Perth, Western Australia, Nov. 2001. (Summary) This paper presents a neural network based high-speed system to detect faces in any visual scene. This paper proposes a high-speed and accurate method to search for human faces using a "Knowledge" pruned small sized neural network, and skin colour detection using threshold method with confirmation by a skin colour detection neural network (TSCD). This project is made up of two parts: the face detecting system (FDS) and the TSCD. The FDS that is used to detect faces is made up of a knowledge pruned face locator, a down sampler, and a merger. The TSCD does a high-speed reduction of the face search area to skin regions (and then to face candidates). The TSCD assumes, correctly, that a human face (without wearing any mask or painting) in a visual scene can only be found in a skin colour region. However, all skin regions containing faces must be found otherwise the overall system accuracy goes down. (Link to Search Site for Scientific Articles) ● Summary page in Scopus @ Elsevier: 2-s2.0-8344247902 (Elsevier: Scopus)
177.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Improved Searching Speed for Human Face Detection in Visual Scenes using Neural Networks, Proc. of International Conference on Neural Information Processing, No.FBP-30, 1-6, Taejon, Nov. 2000. (Summary) 本国際会議論文は，カラー画像中から人物顔を高速に検出するための方法を提案している．特に，顔の肌色特徴及び顔の幾何学的特長をニューラルネットワークにより検出し，かつ高速に実現する方法である．本方法は複数顔にも対応可能であり，カラー顔画像に対する計算機シミュレーションにより，その有効性を定量的に検証している．

Proceeding of Domestic Conference:

1.	TACHIBANA Fumiaki, Kenji Terada and Stephen Githinji Karungaru : 画像処理による部屋の乱雑度判定, ビジョン技術の実利用ワークショップ2023, No.IS3-10, 424-429, Dec. 2023. (Keyword) image processing / pattern recognition / human sensing
2.	FUMIAKI Tachibana, Kenji Terada and Stephen Githinji Karungaru : 画像処理による作業空間の清浄度の判定, 令和5年度計測自動制御学会四国支部学術講演会, No.PS1-01, Dec. 2023. (Keyword) computer vision / image processing / human sensing / pattern recognition
3.	Hiroto Kusatsu, Kenji Terada and Stephen Githinji Karungaru : VR を用いた仮想試着システム, 2023電気・電子・情報関係学会四国支部連合大会, No.13-33, Sep. 2023. (Keyword) computer vision / image processing / human / pattern recognition
4.	Shunsuke Izutani, Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 監視カメラからの歩行者の手荷物認識, 2023電気・電子・情報関係学会四国支部連合大会, No.13-32, Sep. 2023. (Keyword) computer vision / image processing / human / pattern recognition
5.	Kensuke Yamamoto, Kenji Terada and Stephen Githinji Karungaru : HMDを用いた拡張現実による画力向上のための練習システム, 2023電気・電子・情報関係学会四国支部連合大会, No.13-29, Sep. 2023. (Keyword) computer vision / image processing / human / pattern recognition / arts
6.	FUMIAKI Tachibana, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた空中文字認識, 令和4年度計測自動制御学会四国支部学術講演会, No.PS2-23, 153-158, Dec. 2022. (Keyword) computer vision / image processing / human sensing / pattern recognition
7.	Mizuki Matsumoto, Takumi Murakami, Kenji Terada and Stephen Githinji Karungaru : 空撮映像を用いたフットサル行動解析, 令和4年度計測自動制御学会四国支部学術講演会, No.PS2-12, 119-124, Dec. 2022. (Keyword) computer vision / image processing / virtual reality / pattern recognition
8.	TAKAHASHI Genki, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた特徴点による口の動きの観測, 令和4年度計測自動制御学会四国支部学術講演会, No.PS1-22, 74, Dec. 2022. (Keyword) computer vision / image processing / human sensing / pattern recognition
9.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 監視カメラからの歩行者の手荷物認識, 令和4年度計測自動制御学会四国支部学術講演会, No.PS1-10, 29-34, Dec. 2022. (Keyword) computer vision / image processing / deep learning / pattern recognition
10.	Gohki Hashimoto, Kenji Kuramoto, Kenji Terada and Stephen Githinji Karungaru : VDT作業者のドライアイ防止のためのまばたき検知, 令和4年度計測自動制御学会四国支部学術講演会, No.PS1-15, 49-53, Dec. 2022. (Keyword) computer vision / image processing / human sensing / pattern recognition
11.	TAKAHASHI Genki, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた読唇の試み, 2022電気・電子・情報関係学会四国支部連合大会, No.13-8, 105, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
12.	FUMIAKI Tachibana, Kenji Terada and Stephen Githinji Karungaru : Webカメラによる空中指先文字認識, 2022電気・電子・情報関係学会四国支部連合大会, No.13-7, 104, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
13.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた置き引き・遺失物の自動検出, 2022電気・電子・情報関係学会四国支部連合大会, No.13-1, 98, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
14.	YOSHIKAZU Kawai, Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : HMDを用いた拡張現実によるピアノ演奏の支援, 2022電気・電子・情報関係学会四国支部連合大会, No.13-6, 103, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
15.	Mizuki Matsumoto, Takumi Murakami, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いたUAV撮影によるフットサルの映像解析, 2022電気・電子・情報関係学会四国支部連合大会, No.13-5, 102, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
16.	Gohki Hashimoto, Kenji Kuramoto, Kenji Terada and Stephen Githinji Karungaru : 健康管理におけるVDT作業者の顔の向きに影響を受けないまばたき検知, 2022電気・電子・情報関係学会四国支部連合大会, No.13-2, 99, Sep. 2022. (Keyword) computer vision / image processing / human / pattern recognition
17.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : Automatic Detection of Lost and Found Items Using Deep Learning and Image Processing, 第27回知能メカトロニクスワークショップ, No.IM9-1, 134-138, Sep. 2022. (Keyword) image processing / pattern recognition / human sensing / deep learning
18.	Gohki Hashimoto, Kenji Kuramoto, Kenji Terada and Stephen Githinji Karungaru : Monitoring of Pests in Agricultural Houses using A Mobile Device, 第27回知能メカトロニクスワークショップ, No.IM8-1, 118-122, Sep. 2022. (Keyword) image processing / pattern recognition / human sensing / face
19.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 画像処理による置き引き・遺失物の検出, 第28回画像センシングシンポジウム(SSII2022), No.IS1-24, Jun. 2022. (Keyword) image processing / pattern recognition / 監視 / 防犯
20.	Shingo Iwai, Kenji Terada and Stephen Githinji Karungaru : VR空間中でのキーボードによる文字入力, 令和3年度計測自動制御学会四国支部学術講演会, No.PS2-16, 157-162, Dec. 2021. (Keyword) computer vision / image processing / virtual reality / pattern recognition
21.	Mizuki Matsumoto, Takumi Murakami, Kenji Terada and Stephen Githinji Karungaru : フットサルにおける映像解析及び戦術支援, 令和3年度計測自動制御学会四国支部学術講演会, No.PS1-26, 87-92, Dec. 2021. (Keyword) computer vision / image processing / virtual reality / pattern recognition
22.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 特徴量抽出を用いた手書き文字の上達支援, 令和3年度計測自動制御学会四国支部学術講演会, No.PS1-10, 28-33, Dec. 2021. (Keyword) computer vision / image processing / virtual reality / pattern recognition
23.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 画像処理による手書き文字の上達支援, 電気学会知覚情報研究会, No.PI-21-054, Sep. 2021. (Keyword) computer vision / image processing / human / 文字認識 / 個人認証
24.	Kazuyoshi Toki, Kenji Terada and Stephen Githinji Karungaru : カメラ映像による要介護者の見守り, 2021電気・電子・情報関係学会四国支部連合大会, No.13-5, 137, Sep. 2021. (Keyword) computer vision / image processing / human / monitoring / measurement
25.	Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : HMDによるピアノ演奏の上達支援システムの構築, 2021電気・電子・情報関係学会四国支部連合大会, No.13-4, 136, Sep. 2021. (Keyword) computer vision / image processing / human / music / VR
26.	Masahiro Hara, Kenji Terada and Stephen Githinji Karungaru : 画像処理による手書き文字の上達支援, 2021電気・電子・情報関係学会四国支部連合大会, No.13-3, 135, Sep. 2021. (Keyword) computer vision / image processing / human / 文字認識 / 個人認証
27.	Tomoya Kanji, Kenji Terada and Stephen Githinji Karungaru : 拡張現実によるピアノ演奏システムの構築, 令和2年度計測自動制御学会四国支部学術講演会, No.PS2-15, 128-132, Dec. 2020. (Keyword) computer vision / image processing / virtual reality / Augmented Reality
28.	Ryousuke Tsuji, Kenji Terada and Stephen Githinji Karungaru : 車載カメラを用いた歩行者・自転車の危険検知, 令和2年度計測自動制御学会四国支部学術講演会, No.PS1-05, 17-22, Dec. 2020. (Keyword) computer vision / image processing / human sensing
29.	Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : HMD を用いた拡張現実によるピアノ演奏の支援, 2020電気・電子・情報関係学会四国支部連合大会, No.13-22, Sep. 2020. (Keyword) computer vision / image processing / HMD / 拡張現実
30.	Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : Piano Performance Support Using a Head-mounted Display, 第25回知能メカトロニクスワークショップ, No.IM-4-4, 97-102, Sep. 2020. (Keyword) image processing / pattern recognition / VR
31.	Ryousuke Tsuji, Kenji Terada and Stephen Githinji Karungaru : UAVによるスポーツ映像解析, 令和元年度計測自動制御学会四国支部学術講演会, No.PS1-03(SO1-03), Dec. 2019. (Keyword) computer vision / image processing / human sensing
32.	Ryosuke Tsuji, Kenji Terada and Stephen Githinji Karungaru : ドローンを用いたスポーツ映像解析, 2019電気関係学会四国支部連合大会, No.13-23, Sep. 2019. (Keyword) computer vision / image processing / sports / UAV / ドローン
33.	Shu Yano, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Naoya Kohda, Tomohito Wada and Naka Gotoda : A learning environment of a systematic and tactical style in team sports, The 44th Annual Conference of JSiSE, 213-214, Sep. 2019. (Summary) 集団対戦型フィールドスボーツにおいて，各プレイヤがチームの基本戦術を理解することが大切になる.したがって，各基本戦術を認識し，以後の展開予測までできることが望ましい.本研究では，バスケットボールにおける戦術の適用場面を自動抽出し，シミュレーションと実際の映像を同期させて見せることによって，戦術が適用される場面での判断の基準を形成できるシステムを構築する. (Keyword) 可視化 / チーム戦術 / バスケットボール / simulation
34.	Naoya Kohda, Shu Yano, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada and Naka Gotoda : Improvement of software defense design in feint learning, The 44th Annual Conference of JSiSE, 169-170, Sep. 2019. (Summary) 本研究では，バスケットボールの 1 対 1 の場面におけるフェイント動作について取り上げる. その学習支援として，学習者にソフトウェアで実装したディフェンスを提示する.このディフェンスを突破する練習を行う環境の設計に関する改善を図る.フェイント動作を身体部位の動作の仕方に着目し分析する.そのために事前に撮影した動画を解析し，学習者ごとのモデル化を行い，それに対応するディフェンスの挙動を提案する. (Keyword) 学習支援 / 支援モデル / 統合運動 / フェイント動作
35.	Keisuke Tujimoto, Kenji Terada and Stephen Githinji Karungaru : 教室内カメラによる受講態度の自動評価, 平成30年度計測自動制御学会四国支部学術講演会, No.PS2-20(SO2-20), 142-146, Dec. 2018. (Keyword) computer vision / image processing
36.	Yuuya Kawahara, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた屋外における通行者の交差を考慮した人数計測, 平成30年度計測自動制御学会四国支部学術講演会, No.PS2-08(SO2-08), 107-112, Dec. 2018. (Keyword) computer vision / image processing
37.	Masahiro Okashita, Kenji Terada and Stephen Githinji Karungaru : 画像処理によるVDT作業者の集中度と疲労度計測, 平成30年度計測自動制御学会四国支部学術講演会, No.PS2-06(SO2-06), 99-104, Dec. 2018. (Keyword) computer vision / image processing
38.	Keisuke Tsujimoto, Kenji Terada and Stephen Githinji Karungaru : 教室内カメラを用いた受講態度ログの生成, 平成 30 年度電気関係学会四国支部連合大会, No.13-19, Sep. 2018. (Keyword) computer vision / image processing
39.	Masahiro Okashita, Kenji Terada and Stephen Githinji Karungaru : WebカメラによるVDT作業者の集中度と疲労度計測, 平成 30 年度電気関係学会四国支部連合大会, No.13-18, Sep. 2018. (Keyword) computer vision / image processing
40.	Yuya Kawahara, Kenji Terada and Stephen Githinji Karungaru : 屋外監視カメラによる重なりを考慮した通行人数計測, 平成 30 年度電気関係学会四国支部連合大会, No.13-17, Sep. 2018. (Keyword) computer vision / image processing
41.	Shu Yano, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada and Naka Gotoda : Fundamental discussion for understanding tactics of team-match sports, Journal of Shikoku-Section Joint Convention of the Institutes of Electrical and Related Engineers, 215, Sep. 2018.
42.	幸田尚也, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, 和田智仁 and Naka Gotoda : Breakthrough skill development for one-on-one match in competitive sports, 教育システム情報学会第43回全国大会講演論文集, 83-84, Sep. 2018.
43.	Takuya Ishioka, Naka Gotoda, 米谷雄介, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, 和田智仁, 國枝孝之, Rihito Yaegashi and Toshihiro Hayashi : Development of Sports Support System Using Superimposed Movie with Reflection Materials, 教育システム情報学会第43回全国大会講演論文集, 77-78, Sep. 2018.
44.	Akihiro Yamada, Kenji Terada and Stephen Githinji Karungaru : 画像処理による歩行者の挙動判定, ビジョン技術の実利用ワークショップ2017, No.IS1-C4, 167-171, Dec. 2017. (Keyword) image processing / computer vision / human sensing
45.	Shinya Oshodani, Kenji Terada and Stephen Githinji Karungaru : 監視カメラを用いた自転車の危険走行の検知, 平成29年度計測自動制御学会四国支部学術講演会, No.PS2-05(SO2-05), 102-107, Nov. 2017. (Keyword) computer vision / image processing
46.	Akihiro Yamada, Kenji Terada and Stephen Githinji Karungaru : 画像処理による不審者と高齢者の認識, 平成29年度計測自動制御学会四国支部学術講演会, No.PS2-08(SO2-08), 115-119, Nov. 2017. (Keyword) computer vision / image processing
47.	Yuuya Yamase, Kenji Terada and Stephen Githinji Karungaru : 監視カメラによる点字ブロック上の障害物検知, 平成29年度計測自動制御学会四国支部学術講演会, No.PS2-04(SO2-04), 96-101, Nov. 2017. (Keyword) computer vision / image processing
48.	Tomoya Sasaki, Kenji Terada and Stephen Githinji Karungaru : 画像処理による道路標識認識, 平成29年度計測自動制御学会四国支部学術講演会, No.PS2-03(SO2-03), 93-95, Nov. 2017. (Keyword) computer vision / image processing
49.	Kosuke Hasui, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Toshihiro Hayashi and Rihito Yaegashi : Proposal of the Motion Learning System Using Sports Onomatopoeia and Visual Feedback, Journal of Shikoku-Section Joint Convention of the Institutes of Electrical and Related Engineers, 209, Sep. 2017.
50.	Akira Nakahara, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Toshihiro Hayashi and Rihito Yaegashi : Proposal of Motion Learning System by Subdividing Motor Skill, Journal of Shikoku-Section Joint Convention of the Institutes of Electrical and Related Engineers, 208, Sep. 2017.
51.	Akihiro Yamada, Kenji Terada and Stephen Githinji Karungaru : 画像処理による歩行者の行動判定, 平成 29 年度電気関係学会四国支部連合大会, No.13-22, 156, Sep. 2017. (Keyword) computer vision / image processing
52.	Tomoya Sasaki, Kenji Terada and Stephen Githinji Karungaru : 車載カメラによる道路標識の自動認識, 平成 29 年度電気関係学会四国支部連合大会, No.13-21, 155, Sep. 2017. (Keyword) computer vision / image processing
53.	Yuuya Yamase, Kenji Terada and Stephen Githinji Karungaru : 画像処理による点字ブロックの自動認識, 平成 29 年度電気関係学会四国支部連合大会, No.13-20, 154, Sep. 2017. (Keyword) computer vision / image processing
54.	Akihiro Yamada, Kenji Terada and Stephen Githinji Karungaru : 画像処理による歩行者の行動認識, 平成29年電気学会電子・情報・システム部門大会, No.MC6-6, 1179-1183, Sep. 2017. (Keyword) computer vision / image processing
55.	Tomoya Sasaki, Kenji Terada and Stephen Githinji Karungaru : 車載カメラによる道路標識の自動認識, 平成29年電気学会電子・情報・システム部門大会, No.MC6-5, 1176-1178, Sep. 2017. (Keyword) computer vision / image processing
56.	Takuya Ishioka, Naka Gotoda, Kenji Matsuura, Stephen Githinji Karungaru, Yuji Kobayashi, Toshihiro Hayashi, Rihito Yaegashi and Kenichi Fujimoto : Learning Support Environment for Sports Onomatopoeia Using Wearable Device, 教育システム情報学会第42回全国大会講演論文集, 1-2, Aug. 2017.
57.	Takehiko Yoshikawa, Kohta Sugawara, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : A Wearable System for Learning Support on Integrative and Repetitive Exercise, 教育システム情報学会第42回全国大会講演論文集, 243-244, Aug. 2017.
58.	Kohta Sugawara, Takehiko Yoshikawa, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Learning Support for Development of Integrated Motor-skill under Combining Trainings, 教育システム情報学会第42回全国大会講演論文集, 187-188, Aug. 2017.
59.	Shuhei Koyanagi, Kenji Terada and Stephen Githinji Karungaru : 建物内の多地点カメラを用いた人物追跡システム, ビジョン技術の実利用ワークショップ2016, No.IS1-15, 132-135, Dec. 2016. (Keyword) image processing / computer vision / human sensing
60.	Yoshikawa Takehiko, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Skill Learning Support System Focusing on Rhythm Fitting, Journal of Shikoku-Section Joint Convention of the Institutes of Electrical and Related Engineers, 267, Sep. 2016.
61.	Tomohiro Ishino, Kenji Terada and Stephen Githinji Karungaru : 前方・後方・内部カメラを用いた運転支援システム, 電気学会電子·情報·システム部門大会論文集, No.PS5-5, Aug. 2016. (Keyword) computer vision / image processing / human sensing
62.	Yuji Murakami, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた出入り口付近の不審者検知, 電気学会電子·情報·システム部門大会論文集, No.PS5-4, Aug. 2016. (Keyword) computer vision / image processing / human sensing
63.	Takuya Ishioka, Naka Gotoda, Kenji Matsuura, Stephen Githinji Karungaru, Rihito Yaegashi and Toshihiro Hayashi : Proposal of a Training Environment with Feedback based on Individual Perceptual Preference in Motor Skill Learning, 教育システム情報学会第41回全国大会講演論文集, 281-282, Aug. 2016.
64.	Kohta Sugawara, Hiroshi Toyooka, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : Learning support on combining primitive motions for repetitive movement, 教育システム情報学会第41回全国大会講演論文集, 117-118, Aug. 2016.
65.	Hiroshi Toyooka, Kohta Sugawara, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : A Learning Support System on Body Control for Repetitive Motions with Operating Instrument, 教育システム情報学会第41回全国大会講演論文集, 119-120, Aug. 2016.
66.	Masaya Takahashi, Kenji Terada and Stephen Githinji Karungaru : すれ違いや追い抜きを考慮した通行人数計測, 第21回知能メカトロニクスワークショップ, No.1C1-3, Aug. 2016. (Keyword) computer vision / image processing / human sensing
67.	Kenshiro Kato, Kenji Terada and Stephen Githinji Karungaru : USBカメラを用いたVDT作業者の疲労度検出, 第21回知能メカトロニクスワークショップ, No.1B1-3, Aug. 2016. (Keyword) computer vision / image processing / human sensing
68.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : 複数次元特徴量を用いた室内環境の3次元モデリング, 第22回画像センシングシンポジウム, No.IS3-1, Jun. 2016.
69.	Nozomi Maitani, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた自転車の行動検出, ビジョン技術の実利用ワークショップ2015, No.IS2-7, Dec. 2015. (Keyword) image processing / computer vision / security
70.	Tatsuroh Murakami, Masafumi Nishino, Kenji Terada and Stephen Githinji Karungaru : ランニングフォームの自動解析アプリの開発, ビジョン技術の実利用ワークショップ2015, No.IS1-22, Dec. 2015. (Keyword) image processing / computer vision / sports / human sensing
71.	Shinya Yoshioka, Kenji Matsuura, Naka Gotoda and Stephen Githinji Karungaru : A Study on Supporting Improvement of Skills on Rope Skipping from Single-Bounce to Double-Unders, 教育システム情報学会第40回全国大会講演論文集, 125-126, Sep. 2015.
72.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : Kinectを用いた空間の3次元モデリング, 第21回画像センシングシンポジウム, No.IS1-26, Jun. 2015.
73.	Tatsuro Murakami, Mayumi Ooset, Kenji Terada and Stephen Githinji Karungaru : 全方位カメラを用いた移動ロボットの自動走行, ビジョン技術の実利用ワークショップ2014, No.IS2-4, Dec. 2014. (Keyword) image processing / computer vision / security / human sensing
74.	Taishi Kamei, Kenji Terada, Stephen Githinji Karungaru and Marina Niki : カメラ位置に依存しない歩容認識, ビジョン技術の実利用ワークショップ2014, No.IS2-20, Dec. 2014. (Keyword) image processing / computer vision / security / human sensing
75.	Eiji Takeji, Tomoya Morisawa, Kenji Terada and Stephen Githinji Karungaru : AndroidOSを用いた聴講者の行動解析, 第19回知能メカトロニクスワークショップ, No.B2-3, Jul. 2014.
76.	Yusaku Yamazaki, Kenji Terada and Stephen Githinji Karungaru : Air文字認識を用いた入力インタフェース, 第19回知能メカトロニクスワークショップ, No.A2-2, Jul. 2014.
77.	Ryo Hada, Ryo Munetsugu, Kenji Terada and Stephen Githinji Karungaru : クワッドヘリコプタを用いた未知領域のマップ作成システム, 第20回画像センシングシンポジウム, No.IS2-04, Jun. 2014.
78.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : BCIのための簡易計測装置を用いた生体信号の解析, 電気学会C部門大会, GS13-3, Sep. 2013.
79.	Ruka Kawabata, Kenji Terada and Stephen Githinji Karungaru : 出入口付近における不審行動の検知, 第18回知能メカトロニクスワークショップ, No.V1-5, Aug. 2013.
80.	Junpei Yamamoto, Kenji Terada and Stephen Githinji Karungaru : 交通標識と道路標示認識による運転支援, 第18回知能メカトロニクスワークショップ, No.V1-3, Aug. 2013.
81.	Ruka Kawabata, Kenji Terada and Stephen Githinji Karungaru : 監視カメラを用いた侵入行為の検出, 第19回画像センシングシンポジウム, No.IS1-05, Jun. 2013.
82.	Kosuke Hattori, Kenji Terada and Stephen Githinji Karungaru : 歩容特徴を用いた人物認証, 2012年度計測自動制御学会四国支部講演会, No.SO2-2, Nov. 2012. (Keyword) computer vision / image processing
83.	Shinichi Fujita, Kenji Terada and Stephen Githinji Karungaru : webカメラを用いた計算機室の監視システム, 2012年度計測自動制御学会四国支部講演会, No.SO2-1, Nov. 2012. (Keyword) computer vision / image processing
84.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : FG 視覚センサを用いた全身 3D モデルの作成, 平成24年度電気関係学会四国支部連合大会, No.13-6, Sep. 2012. (Keyword) computer vision / image processing
85.	Tomoya Morisawa, Kenji Terada and Stephen Githinji Karungaru : GPGPU を用いた心臓弁の動き解析, 平成24年度電気関係学会四国支部連合大会, No.13-5, Sep. 2012. (Keyword) computer vision / image processing
86.	Kosuke Hattori, Kenji Terada and Stephen Githinji Karungaru : 歩容特徴を用いた個人認証, 平成24年度電気関係学会四国支部連合大会, No.13-4, Sep. 2012. (Keyword) computer vision / image processing
87.	Shinichi Fujita, Kenji Terada and Stephen Githinji Karungaru : 画像処理による計算機室の監視システム, 平成24年度電気関係学会四国支部連合大会, No.13-2, Sep. 2012. (Keyword) computer vision / image processing
88.	Takayuki Kashihara, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた人数計測, 平成24年度電気関係学会四国支部連合大会, No.13-1, Sep. 2012. (Keyword) computer vision / image processing
89.	Takayuki Kashihara, Kenji Terada and Stephen Githinji Karungaru : 交差した計測線による人数計測, 第17回知能メカトロニクスワークショップ, No.V3-4, Aug. 2012.
90.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : FG 視覚センサによる全身3次元モデリング, 第17回知能メカトロニクスワークショップ, No.V1-5, Aug. 2012.
91.	Shinichi Fujita, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた計算機室の監視システム, 第18回画像センシングシンポジウム, No.IS2-10, Jun. 2012.
92.	Kosuke Hattori, Kenji Terada and Stephen Githinji Karungaru : 歩容特徴による個人認証, 第18回画像センシングシンポジウム, No.IS2-09, Jun. 2012.
93.	Ryo Hada, Kenji Terada and Stephen Githinji Karungaru : FG視覚センサを用いた全身3Dモデリング, 第18回画像センシングシンポジウム, No.IS1-02, Jun. 2012.
94.	Ryo Munetsugu, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : Crack detection using the Unmanned helicopter picture, ロボティクス・メカトロニクス講演会2012, No.2A2-J03, May 2012. (Keyword) computer vision / image processing / Humanoid robot
95.	Yoshiki Takamatsu, Kenji Terada and Stephen Githinji Karungaru : マーカーを用いたフリースローの練習支援, DIA2012, No.I-18, 187-190, Mar. 2012.
96.	Kensuke Kawamura, Kenji Terada and Stephen Githinji Karungaru : WEBカメラを用いた金魚監視システム, DIA2012, No.I-12, 156-160, Mar. 2012.
97.	Kazuma Nitta, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いたバーチャルダーツ, 2011年度計測自動制御学会四国支部講演会, No.SO2-08, Nov. 2011. (Keyword) computer vision / image processing
98.	Naru Iwado, Kenji Terada and Stephen Githinji Karungaru : 固定カメラを用いた不審者検知システム, 2011年度計測自動制御学会四国支部講演会, No.SO2-06, Nov. 2011. (Keyword) computer vision / image processing
99.	Hiroshige Kawashima, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : ARマーカ認識技術を用いた飛行船の自動航行, 2011年度計測自動制御学会四国支部講演会, No.SO1-10, Nov. 2011. (Keyword) computer vision / image processing / Humanoid robot
100.	Kensuke Kawamura, Kenji Terada and Stephen Githinji Karungaru : USBカメラを用いた金魚監視システム, 2011年度計測自動制御学会四国支部講演会, No.SO2-05, Nov. 2011. (Keyword) computer vision / image processing
101.	Soichiro Takahashi, Kenji Terada and Stephen Githinji Karungaru : 空中指文字認識を用いたインテリジェントルーム, 2011年度計測自動制御学会四国支部講演会, No.SO1-03, Nov. 2011. (Keyword) computer vision / image processing
102.	Hikaru Mori, Kenji Terada and Stephen Githinji Karungaru : 2つのカメラを用いたバーチャルチェロ, 2011年度計測自動制御学会四国支部講演会, No.SO1-01, Nov. 2011. (Keyword) computer vision / image processing
103.	Kazunori Tsuda, Kenji Terada and Stephen Githinji Karungaru : 画像処理を用いた会場監視計測システム, 平成23年度電気関係学会四国支部連合大会, No.13-27, Sep. 2011. (Keyword) computer vision / image processing
104.	Yuki Sato, Kenji Terada and Stephen Githinji Karungaru : サングラス型ビデオカメラを用いた視線認識, 平成23年度電気関係学会四国支部連合大会, No.13-27, Sep. 2011. (Keyword) computer vision / image processing
105.	Hikaru Mori, Kenji Terada and Stephen Githinji Karungaru : USBカメラを用いた仮想チェロ演奏, 平成23年度電気関係学会四国支部連合大会, No.13-26, Sep. 2011. (Keyword) computer vision / image processing
106.	Kazuma Nitta, Kenji Terada and Stephen Githinji Karungaru : 2方向のカメラ画像を用いたバーチャルダーツ, 平成23年度電気関係学会四国支部連合大会, No.13-25, Sep. 2011. (Keyword) computer vision / image processing
107.	Hiroshige Kawashima, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : AR マーカを用いた飛行船の自動航行, 2011年度精密工学会秋季大会学術講演会, No.O-20, Sep. 2011. (Keyword) computer vision / image processing / Humanoid robot
108.	Naru Iwado, Kenji Terada and Stephen Githinji Karungaru : カメラを用いた不審者の自動検出, 第17回画像センシングシンポジウム, No.IS3-02, Jun. 2011.
109.	Kazuma Nitta, Kenji Terada and Stephen Githinji Karungaru : 多方向カメラを用いたバーチャルダーツ, 第17回画像センシングシンポジウム, No.IS2-07, Jun. 2011.
110.	Soichiro Takahashi, Kenji Terada and Stephen Githinji Karungaru : 空中文字認識を用いたインテリジェントルームの構築, 第17回画像センシングシンポジウム, No.IS1-03, Jun. 2011.
111.	Hiroshige Kawashima, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : カメラ画像を用いたラジコンヘリの操縦支援システム, ロボティクス・メカトロニクス講演会2011, No.1P1-M08, May 2011.
112.	Yuki Sato, Stephen Githinji Karungaru and Kenji Terada : サングラス型ビデオカメラ画像のイメージモザイク, 動的画像処理実利用化ワークショップ(DIA2011), No.I2-30, Mar. 2011.
113.	Kazuma Nitta, Stephen Githinji Karungaru and Kenji Terada : カメラを用いたバーチャルダーツ, 動的画像処理実利用化ワークショップ(DIA2011), No.I2-27, Mar. 2011.
114.	Takahashi Soichiro, Stephen Githinji Karungaru and Kenji Terada : 空中文字認識を用いた知能化した室内環境システムの構築, 動的画像処理実利用化ワークショップ(DIA2011), No.I2-24, Mar. 2011.
115.	Tetsuya Fukushima, Stephen Githinji Karungaru and Kenji Terada : Webカメラを用いた観賞魚の育成支援システム, 動的画像処理実利用化ワークショップ(DIA2011), No.I1-28, Mar. 2011.
116.	Hikaru Mori, Stephen Githinji Karungaru and Kenji Terada : Webカメラを用いたバーチャルチェロ, 動的画像処理実利用化ワークショップ(DIA2011), No.I1-24, Mar. 2011.
117.	Naru Iwado, Stephen Githinji Karungaru and Kenji Terada : USBカメラを用いた不審者の自動認識システム, 動的画像処理実利用化ワークショップ(DIA2011), No.I1-18, Mar. 2011.
118.	Yusuke Watabe, Stephen Githinji Karungaru and Kenji Terada : Webカメラを用いた作業者の状態把握システム, 動的画像処理実利用化ワークショップ(DIA2011), No.I1-15, Mar. 2011.
119.	Yohei Nakayama, Stephen Githinji Karungaru and Kenji Terada : GPGPUを用いた人の高速トラッキング, 動的画像処理実利用化ワークショップ(DIA2011), No.I1-11, Mar. 2011.
120.	Hiroshige Kawashima, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : カメラを用いたラジコンヘリの自動着陸, 動的画像処理実利用化ワークショップ2011, 77-78, Mar. 2011.
121.	Hiroshige Kawashima, Kenji Terada, Stephen Githinji Karungaru and Masafumi Miwa : Control support in Radio controller helicopter by Image processing, 電気学会システム研究会ST-11-001~013, 17-21, Mar. 2011.
122.	Yuuichiro Fukumoto, Stephen Githinji Karungaru and Kenji Terada : 複数の表色系と領域分割を用いた人数計測, 第53回自動制御連合講演会, No.578, Nov. 2010.
123.	Satoshi Yamashita, Stephen Githinji Karungaru and Kenji Terada : FG視覚センサを用いた人物の3次元モデリング, 第53回自動制御連合講演会, No.577, Nov. 2010.
124.	Yohei Nakayama, Stephen Githinji Karungaru and Kenji Terada : GPGPUを用いた人の高速トラッキング, 2010年度計測自動制御学会四国支部学術講演会, No.244, Nov. 2010. (Keyword) image processing / computer vision / human sensing
125.	Kazunori Tsuda, Stephen Githinji Karungaru and Kenji Terada : 画像処理によるバーチャルダーツ, 2010年度計測自動制御学会四国支部学術講演会, No.243, Nov. 2010. (Keyword) image processing / computer vision / human sensing
126.	Yohei Nakayama, Stephen Githinji Karungaru and Kenji Terada : GPGPUを用いた人の高速トラッキング, 2010年精密工学会秋季大会, No.G-21, Sep. 2010.
127.	Yuuichiro Fukumoto, Stephen Githinji Karungaru and Kenji Terada : 複数の表色系を用いた人数計測, 平成22年度電気関係学会四国支部連合大会, No.13-32, Sep. 2010.
128.	Kazunori Tsuda, Stephen Githinji Karungaru and Kenji Terada : 画像処理によるバーチャルダーツ, 平成22年度電気関係学会四国支部連合大会, No.13-29, Sep. 2010.
129.	石谷淳, 白石卓也, Momoyo Ito, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : モーションステレオを用いた移動ロボット向けユーザインタフェース, 平成22年電気学会電子・情報・システム部門大会講演論文集, 694-697, Sep. 2010.
130.	田岡文利, Momoyo Ito, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : 証明変動に頑健な放置物検出法, 平成22年電気学会電子・情報・システム部門大会講演論文集, 689-693, Sep. 2010.
131.	Yohei Nakayama, Stephen Githinji Karungaru and Kenji Terada : GPGPUを用いた人の高速トラッキング, 平成22年度電気関係学会四国支部連合大会, No.13-38, Sep. 2010.
132.	Satoshi Yamashita, Stephen Githinji Karungaru and Kenji Terada : FG視覚センサによる人の超解像モデリング, 平成22年度電気関係学会四国支部連合大会, No.13-33, Sep. 2010.
133.	Koki Nakagawa, Tsutomu Takeshita, Stephen Githinji Karungaru and Kenji Terada : カメラ画像を用いたギターのバーチャル演奏, 平成22年度電気関係学会四国支部連合大会, No.13-31, Sep. 2010.
134.	Yuuichiro Fukumoto, Stephen Githinji Karungaru and Kenji Terada : 混雑状況下における人数計測, 第16回画像センシングシンポジウム, No.IS4-20, Jun. 2010.
135.	Satoshi Yamashita, Stephen Githinji Karungaru and Kenji Terada : FG視覚センサを用いた人の超解像モデリング, 第16回画像センシングシンポジウム, No.IS1-09, Jun. 2010.
136.	Takuya Akashi, 若佐裕治, 田中幹也, Stephen Githinji Karungaru and Minoru Fukumi : 遺伝的アルゴリズムを用いた口唇の3 次元情報の取得, FANシンポジウム2008, 11-14, Oct. 2008.
137.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : Simple-FLDAにおける追加型アルゴリズムの提案, 第18回インテリジェント・システム・シンポジウム(FAN 2008), 21-24, Oct. 2008.
138.	Tadahiro Oyama, Satoru Tsuge, Stephen Githinji Karungaru, Yasue Mitsukura and Minoru Fukumi : 判別分析における高速な追加学習アルゴリズムの一提案, 電気学会電子・情報・システム部門大会講演プラグラム集, 286-289, Aug. 2008.
139.	Choge Hillary, Stephen Githinji Karungaru, Satoru Tsuge and Minoru Fukumi : A Fourier-Space Palmprint Feature Extraction Method for Personal Identification, 電気学会電子・情報・システム部門大会講演プラグラム集, 303-307, Aug. 2008.
140.	Minoru Fukumi, Stephen Githinji Karungaru, 中野実代子, Satoru Tsuge, Takuya Akashi and Yasue Mitsukura : 超高速学習型統計アルゴリズムによる特徴抽出, シミュレーション&ゲーミング学会秋期大会, Oct. 2007.
141.	近藤将之, Stephen Githinji Karungaru, Satoru Tsuge, Minoru Fukumi and Yasue Mitsukura : ニューラルネットワークによる画像へのキーワード付加, Proceedings of the Japan Industry Applications Society Conference, II_83-86, Aug. 2007.
142.	Minoru Fukumi, Stephen Githinji Karungaru, 明石卓也, 中野実代子 and Yasue Mitsukura : 新統計的学習アルゴリズムによる超高速特徴生成, 高速信号処理応用技術学会2007年研究会, 27, Jul. 2007.
143.	竹内洋平, Minoru Fukumi, Norio Akamatsu, Stephen Githinji Karungaru and 小澤誠一 : Character Recognition for Malaysian License Plate, システム制御·情報学会講演会, 671-672, May 2006.
144.	中道功, Stephen Githinji Karungaru, Minoru Fukumi, Yasue Mitsukura and 安友基勝 : Extraction of the Liver Tumor in CT Image by GA, システム制御·情報学会講演会, 667-668, May 2006.
145.	Takuya Akashi, 若佐裕治, 田中幹也, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Eye Detection by Genetic Algorithms, システム制御·情報学会講演会, 599-600, May 2006.
146.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Facial Expression Creation using Image Warping and Neural Networks, Proc. of JACC'2003, No.FP2-02-1, 1120-1122, Nov. 2003. (Keyword) Face expression / Warping and Neural network
147.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Skin Color Recovery from Over-Exposed Images Using Neural Networks, IEICE Technical report (NC 2002), Vol.102, No.157, 7-12, Jun. 2002.

Et cetera, Workshop:

1.	Kensuke Yamamoto, Kenji Terada and Stephen Githinji Karungaru : HMDを用いた拡張現実による画力向上のための練習システム, 電気学会知覚情報研究会, No.PI-23-046, 7-12, Oct. 2023. (Keyword) computer vision / image processing / human / human sensing / VR
2.	FUMIAKI Tachibana, Kenji Terada and Stephen Githinji Karungaru : 空中文字のWebカメラを用いた認識, 電気学会知覚情報研究会, No.PI-22-040, Oct. 2022. (Keyword) computer vision / image processing / human / human sensing / pattern recognition
3.	Mizuki Matsumoto, Takumi Murakami, Kenji Terada and Stephen Githinji Karungaru : UAVを用いたスポーツ映像解析と戦術支援, 電気学会知覚情報研究会, No.PI-21-055, Oct. 2021. (Keyword) computer vision / image processing / human / sports / ドローン
4.	Tomoya Kaji, Kenji Terada and Stephen Githinji Karungaru : ピアノ演奏の状況認識とHMDを用いた支援, 電気学会知覚情報研究会, No.PI-21-052, Oct. 2021. (Keyword) computer vision / image processing / human / music / VR
5.	Takuya Ishioka, Naka Gotoda, Ryota Akagi, Yuki Hirasawa, Kenji Matsuura, Hiroki Tanioka, Stephen Githinji Karungaru, Tomohito Wada, Yusuke Kometani, Takayuki Kunieda, Rihito Yaegashi and Toshihiro Hayashi : Evaluation of the Video System for Motor Skill Training Superimposing Symbols, IEICE Technical Report, Vol.ET2018-111, 135-140, Mar. 2019.
6.	Takehiko Yoshikawa, Kenji Matsuura, Stephen Githinji Karungaru and Naka Gotoda : A Form Analysis for Harmonizing Timing Among Movements of Body Portions, JSiSE Resaeach Report, Vol.33, No.4, 7-12, Oct. 2018.
7.	Masahiro Okashita, Kenji Terada and Stephen Githinji Karungaru : 画像処理を⽤いたVDT作業者の集中度と疲労度計測, The Papers of Technical Meeting, IEE JAPAN, No.PI-18-074, Oct. 2018. (Keyword) computer vision / image processing
8.	Yuya Kawahara, Kenji Terada and Stephen Githinji Karungaru : 屋外監視カメラを⽤いた⼈物同⼠の重なりを考慮した通⾏⼈数計測, The Papers of Technical Meeting, IEE JAPAN, No.PI-18-073, Oct. 2018. (Keyword) computer vision / image processing
9.	Keisuke Tsujimoto, Kenji Terada and Stephen Githinji Karungaru : 受講態度の自動評価, The Papers of Technical Meeting, IEE JAPAN, No.PI-18-72, Oct. 2018. (Keyword) computer vision / image processing
10.	Kosuke Hasui, Akira Nakahara, Takuya Ishioka, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Yusuke Kometani, Toshihiro Hayashi and Rihito Yaegashi : Physical Learning Support System Using Comic-Font Expressing Intuitive Intention of Sports Onomatopoeia, IEICE Technical Report, Vol.117, No.469, 77-82, Mar. 2018.
11.	Akira Nakahara, Kosuke Hasui, Takuya Ishioka, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Yusuke Kometani, Toshihiro Hayashi and Rihito Yaegashi : A Training Environment with Sharing Teaching Video and Sensor for Learner to Recognize Elite Motion, IEICE Technical Report, Vol.117, No.469, 71-76, Mar. 2018.
12.	Kosuke Hasui, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Toshihiro Hayashi and Rihito Yaegashi : Proposal of a Motion Learning Using Comic-Font Representation System, IEICE Technical Report, Vol.117, No.296, 61-64, Nov. 2017.
13.	Akira Nakahara, Takuya Ishioka, Naka Gotoda, Takayuki Kunieda, Kenji Matsuura, Stephen Githinji Karungaru, Toshihiro Hayashi and Rihito Yaegashi : Proposal of a Wearable System Supporting Comprehension of Sports Onomatopoeia, IEICE Technical Report, Vol.117, No.296, 57-60, Nov. 2017.
14.	Shinya Oshodani, Kenji Terada and Stephen Githinji Karungaru : 監視カメラによる自転車の危険走行の検出, The Papers of Technical Meeting, IEE JAPAN, No.PI-17-091, 25-30, Oct. 2017. (Keyword) computer vision / image processing
15.	Yuuya Yamase, Kenji Terada and Stephen Githinji Karungaru : 画像処理による点字ブロックの自動認識, The Papers of Technical Meeting, IEE JAPAN, No.PI-17-093, 37-42, Oct. 2017. (Keyword) computer vision / image processing
16.	Takuya Ishioka, Naka Gotoda, Kenji Matsuura, Stephen Githinji Karungaru, Rihito Yaegashi, Toshihiro Hayashi, Kenichi Fujimoto and Hiroshi Murai : Supporting Individual Motor Learning with Selective Feedback, 教育システム情報学会研究報告, Oct. 2016.
17.	Hikaru Mori, Kenji Terada and Stephen Githinji Karungaru : カメラ画像を用いた仮想チェロの演奏, 電気学会情報処理・次世代産業システム合同研究会, No.IIS-11-038, Apr. 2011.
18.	Tadahiro Oyama, Stephen Githinji Karungaru, Satoru Tsuge, Yasue Mitsukura and Minoru Fukumi : パターン認識における追加学習法, 電子情報通信学会ニューロコンピューティング研究会, Vol.NC2007, Jun. 2007.
19.	小川宜洋, Stephen Githinji Karungaru, Yasue Mitsukura, Minoru Fukumi and Norio Akamatsu : ニューラルネットワークを用いた音楽聴取時の脳波解析, 電子情報通信学会ニューロコンピューティング研究会, Vol.NC2007, Jun. 2007.
20.	Tadahiro Oyama, 松村悠司, Stephen Githinji Karungaru, Yasue Mitsukura and Minoru Fukumi : Recognition of Wrist Motion Pattern by EMG, IEICE Technical Report, Vol.HIP2006-40, 91-95, Jul. 2006. (Keyword) EMG / Neural Network / Simple-PCA / Simple-FLDA (Link to Search Site for Scientific Articles) ● CiNii @ National Institute of Informatics (CRID): 1520572357937265664 (CiNii: 1520572357937265664)
21.	Yasuyuki Takahashi, Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Morphing of Face Image by Feature Extraction, IEICE Technical Report, Vol.HIP2005-27, 43-47, Jul. 2005. (Keyword) Face / Feature / morphing / warping
22.	Stephen Githinji Karungaru, Minoru Fukumi and Norio Akamatsu : Skin Color Recovery from Over-Exposed Images Using Neural Networks, IEICE Technical Report, Vol.120, No.157, 7-12, Jun. 2002. (Keyword) neural network / Cylindrical Metric Method / Over-exposure / skin color reconstruction

Grants-in-Aid for Scientific Research (KAKEN Grants Database @ NII.ac.jp)

Visualization system for performance analysis with multi-object tracking (Project/Area Number: 22K12293 )
Cyberphysical Space Connecting Local and Global Perspectives in Supporting Motor-Skill Development (Project/Area Number: 18H03344 )
Support of improving proficiency in repetitive motor-skills (Project/Area Number: 15K01072 )
Search by Researcher Number (70380110)

Associate Professor : Karungaru, Stephen Githinji

Research

Personal Web Page

Field of Study

Subject of Study

Book / Paper

Book:

Academic Paper (Judged Full Paper):

Academic Letter:

Proceeding of International Conference:

Proceeding of Domestic Conference:

Et cetera, Workshop:

Grants-in-Aid for Scientific Research (KAKEN Grants Database @ NII.ac.jp)