Facial expression recognition based on color lines model and region based processing

Facial expression involves various movements. We present various facial expressions as simple regions on facial area and get recognition rate. There are two steps for obtaining the expression regions. First step is to extract facial area from input image with color lines model and second step is to catch regions of expression on extracted facial area with active contour without edges method as a region based processing. We have tested this presentation method for facial expressions from the open facial expression database JAFFE(Japanese Female Facial Expressions). In this method, we can get a facial expression region without any manual works. In the future, we will compensate for lack of ambiguities among expressions with person specific method and this method will be extended to image sequence.