Abstract The learning method for hand gesture recognition system based on vision is commonly off-line, which results in repeated off-line learning when new hand gestures come. Its real-time performance, expansibility and robustness are poor. In this paper, a method named online principle component analysis (PCA) with adaptive subspace is proposed for hand gesture recognition. The subspace is updated online by calculating PCA of sample coefficients. The subspace updating strategy is adjusted according to the degree of difference between new sample and learned sample. The algorithm is able to adapt to different situations and reduce the cost of calculation and storage. The incremental online learning and recognition of hand gestures are realized by the proposed algorithm. Experimental results show that the proposed method solves the unknown hand gesture problem, realizes online hand gesture accumulation and updating and improves the recognition performance of system.
[1] Steil1 J J, Wersing H. Recent Trends in Online Learning for Cognitive Robot // Proc of the European Symposium on Artificial Neural Networks. Bruges, Belgium, 2006: 77-87 [2] Manresa C, Varona J, Mas R, et al. Real-Time Hand Tracking and Gesture Recognition for Human-Computer Interaction. Electronic Letters on Computer Vision and Image Analysis, 2000, 5(3): 96-104 [3] Je H, Kim J, Kim D. Hand Gesture Recognition to Understand Musical Conducting Action // Proc of the 16th IEEE International Conference on Robot Human Interactive Communication. Jeju, Korea, 2007: 163-168 [4] Fang Yikai, Wang Kongqiao, Cheng Jian, et al. A Real-Time Hand Gesture Recognition Method // Proc of the IEEE International Conference on Multimedia and Expo. Beijing, China, 2007: 995-998 [5] Yoon H S, Soh J, Bae Y J, et al. Hand Gesture Recognition Using Combined Features of Location, Angle and Velocity. Pattern Recognition, 2001, 34(7): 1491-1501 [6] Binh N D, Shuchi E, Ejima T. Real-Time Hand Tracking and Gesture Recognition System // Proc of International Conference on Graphics, Vision and Image Processing. Cairo, Egypt, 2005: 362-368 [7] Kirishima T, Sato K, Chihara K. Real-Time Gesture Recognition by Learning and Selective Control of Visual Interest Points. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(3): 351-364 [8] Ren Haibing, Zhu Yuanxin, Xu Guangyou, et al. Hand Gesture Segmentation and Recognition with Complex Backgrounds. Acta Automatica Sinica, 2002, 28(2): 256-261 (in Chinese) (任海兵,祝远新,徐光祐,等.复杂背景下的手势分割与识别.自动化学报, 2002, 28(2): 256-261) [9] Yang Quan, Wang Min. Hand Gesture Recognition Algorithm Based on Euclidean Distance. Microcomputer Information, 2007, 23(25): 265-266 (in Chinese) (杨 全,王 民.基于Euclidean 距离的手势识别. 微计算机信息, 2007, 23(25): 265-266) [10] Kirstein S, Wersing H, Korner E. A Biologically Motivated Visual Memory Architecture for Online Learning of Objects. Neural Networks, 2008, 21: 65-77 [11] Luo Jie, Pronobis A,Caputo B, et al. Incremental Learning for Place Recognition in Dynamic Environments // Proc of the IEEE/RSJ International Conference on Intelligent Robots and Systems. San Diego, USA, 2007: 721-728 [12] Ozawa S, Pang Shaoning, Kasabov N. A Modified Incremental Principal Component Analysis for On-Line Learning of Feature Space and Classifier // Proc of the 8th Pacific Rim International Conference on Artificial Intelligence. Auckland, New Zealand, 2004: 231-240 [13] Jiang Xianhua, Motai Y. Learning by Observation of Robotic Tasks Using On-Line PCA-Based Eigen Behavior // Proc of the IEEE International Symposium on Computational Intelligence in Robotics and Automation. Espoo, Finland, 2005: 391-396 [14] Artac M, Jogan M, Leonardis A. Incremental PCA for On-Line Visual Learning and Recognition // Proc of the 16th International Conference on Pattern Recognition. Quebec, Canada, 2002, Ⅲ: 781-784 [15] Skocaj D, Leonardis A. Weighted and Robust Incremental Method for Subspace Learning // Proc of the IEEE International Conference on Computer Vision. Nice, France, 2003: 1494-1501 [16] Fussenegger M, Roth P M, Bischof H, et al. On-Line, Incremental Learning of a Robust Active Shape Model // Proc of the 28th DAGM Symposium for Pattern Recognition. Berlin, Germany, 2006: 122-130 [17] Neto H V, Nehmzow U. Incremental PCA: An Alternative Approach for Novelty Detection // Proc of the Towards Autonomous Robotic Systems Incorporating the Autumn BiroNet Symposium. London, UK, 2005: 227-233 [18] Peng Juanchun , Gu Lizhong , Su Jianbo. The Hand Tracking for Humanoid Robot Using Camshift Algorithm and Kalman Filter. Journal of Shanghai Jiaotong University, 2006, 40(7): 1161-1165 (in Chinese) (彭娟春, 顾立忠, 苏剑波. 基于Camshift 和Kalman 滤波的仿人机器人手势跟踪. 上海交通大学学报, 2006, 40(7): 1161-1165)
2011, Vol. 24 
