Facial Figure Expression Recognition And Research

With the Affective Computing and the intellectualizedHuman-Machine interactive interface development,the facail exprresion recognition has become a hot research point.This paper makes the finler research on facail expression recognitionin the dynamic video sequence. The first phase is Real-time Face Detection and Tracking in video sequences. The next is Facial Feature ExWacting. Driver fatigue has become an important reason for many traffic accidents. Most of the existing fatigue recognition methods are spatial approaches, and visual features obtained from a single face image are used for classification. Face recognition technology is a friendly and direct way to identify different person as compared with recognition technologies.A method for skin segmentation based on similarity of skin color and dynamic threshold is proposed to improve thespeed and performance of face detection. Firstly, the similarity of skin color is calculated in ycgcr space. Then, the method based on between cluster variance and within-class scatter for selecting the threshold dynamically is pmpesed. Skin color segmentation is implemented according the dynamic threshold. The binary image obtained by skin segmentation is processed in order to eliminate noise. The experimental results show that the proposed algorithm improves the performance of skin segmentation, and can segment skin regions exactly in the complex background to improve the speed and performance of face detection. The innovations of this paper are as follows:(1) Puting forward based on the face of the mouth expression facial fatigue curvature identification.(2) Comprehensive face mouth curvature and eye condition to face fatigue recognition, greatly improving the fatigue recognition rate. (3) For the eyes and mouth set different priority, according to the first eye condition, again according to identify the mouth state to identify fatigue.