Real-time Hand Gesture Recognition System Based on Q6455 DSP Board

This paper presents detailed description of a real-time hand gesture recognition system using embedded DSP board and image processing approaches. Such a system which can identify hand postures and dynamic gestures has manifold potential applications range from sign languages to human computer interaction. We use Q6455 DSP board based on 4 TI-TMS320C6455 DSPs as the computational unit. This versatile signal processing module has powerful computing and interconnection capability. To recognize hand postures, algorithm based on skin color segmentation and geometric invariant feature has been used. During identify dynamic gestures, optical flow tracking approach and direction encoding are adopted. The implementation of high reliable algorithm on DSP board keeps the system robust and efficient. Experimental results show that the proposed system performs well in recognizing hand postures and dynamic gestures real timely. The accuracy and scalability of this system are also soundly proved.

[1]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[2]  Charles A. Bouman,et al.  A simple and efficient face detection algorithm for video database applications , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[3]  Vladimir Pavlovic,et al.  Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Roland T. Chin,et al.  On Image Analysis by the Methods of Moments , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Ying Wu,et al.  View-independent recognition of hand postures , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  L. Udawatta,et al.  Identification of moving obstacles with Pyramidal Lucas Kanade optical flow and k means clustering , 2007, 2007 Third International Conference on Information and Automation for Sustainability.

[8]  Edward J. Delp,et al.  Optimum color spaces for skin detection , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[9]  A. Verri,et al.  Analysis of differential and matching methods for optical flow , 1989, [1989] Proceedings. Workshop on Visual Motion.

[10]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[11]  Guoman Liu,et al.  A High-Performance Scalable Computing System for Real-Time Signal Processing Applications , 2008, 2008 Congress on Image and Signal Processing.

[12]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[13]  P. Anandan,et al.  A computational framework and an algorithm for the measurement of visual motion , 1987, International Journal of Computer Vision.

[14]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[15]  Abbas El Gamal,et al.  Optical flow estimation using high frame rate sequences , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[16]  Chin-Chen Chang.  Feature-preserving algorithm for gesture recognition , 2007 .

[17]  S. Mitra,et al.  Gesture Recognition: A Survey , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[18]  A. Verri,et al.  Differential techniques for optical flow , 1990 .