Fusion of Skin Color and Facial Movement for Facial Expression Recognition

In this paper, based on the combination of skin color and facial movement, the automatic expression recognition algorithm is studied. The image is transformed into YIQ color space by RGB, and image data is extracted in the first dimension of YIQ. Background and skin color are segmented from binary image. Pareto optimization algorithm is used to select facial expression features. This algorithm has less computation, simple structure and fast running speed. It can accurately detect and track the small-angle facial skin color, facial expression changes, facial rotation and occlusion. Experiments show that the proposed algorithm can be well adapted to face rotation at small angles. For the state of human eyes, the algorithm is not affected, and can adapt to the rich facial expression changes and different skin color better, and has a certain stability.