Real-time Gesture Recognition Based on AdaBoost Algorithm and Optical Flow Matching

Focusing on more general and more convenient application, a novel real-time gesture recognition method based on AdaBoost algorithm and optical flow matching was put forward.In detail, the AdaBoost algorithm was used to traverse the whole image for the recognition of static gestures.As to the dynamic gestures, the method combining optical flow with template matching was utilized.The whole system has strong robustness in the recognition of both static and dynamic gestures.