Motion recognition based on face and hand activity detection

In this paper, we develop face and hand activity detection for motion recognition system. In initial stage, a skin color segmentation method for the color image with complex background is presented, which is a mixed skin color segmentation model in both HSI and YCbCr color space constructed. After skin color segmentation, improved face feature extraction method is proposed. Then the improved CAMSHIFT algorithm is used for hand tracking stage. Through computation, the key points of hand and face can be received. Then we establish coordinate system for motion recognition. Simulation results indicate our proposed algorithm has satisfying interactive function in real time and it can be applied in different illumination condition and complex background as well.