A Gesture Recognition Algorithm Using Hausdorff-Like Distance Template Matching Based on the Main Direction of Gesture
暂无分享,去创建一个
Hand gesture of rotation, scaling and translation is the key problem of gesture recognition. This paper proposes a gesture recognition algorithm based on Hausdorff-like distance template matching of gesture main direction. Firstly, we segment hand gesture from video stream. Secondly, we calculate the main direction of gesture in the image, and build a 2D rectangular coordinate system. Then, we clockwise divide the gesture into eight sub-image area along the main direction of gesture and calculate the coordinates of target pixel points in each sub-image area in the 2D rectangular coordinate system. Finally, the algorithm of Hausdorff-like distance template matching is used to recognize the final gesture. Experimental results show that this algorithm can achieve real-time correct recognition of gestures in relatively stable light conditions. The overall recognition rate can reach 95%.
[1] Jovan Popovic,et al. Real-time hand-tracking with a color glove , 2009, SIGGRAPH '09.
[2] Jovan Popović,et al. Real-time hand-tracking with a color glove , 2009, SIGGRAPH 2009.
[3] Yael Edan,et al. Vision-based hand-gesture applications , 2011, Commun. ACM.
[4] Ren Hai. Vision-Based Recognition of Hand Gestures:A Survey , 2000 .
[5] Zhang Liang,et al. Hand Gesture Recognition Based on Hausdorff Distance , 2002 .