This paper describes a new methed of facial expression recognition for Man-Machine Interface. Our method can not only recognize some kinds of facial expressions but also estimate its degree information, and the recognition results can use for many applications of interface. Our method is based on the idea that facial expression recognition can be achieved by extracting a variation from expressionless face ith considering face area as a whole pattern. Using a elastic net model, a varlation of facial expression is represented as motion vectors of the deformed Net from a facial edge image. Then, applying K-L expansion, the change of facial expression represented as the motion vectors of nodes is mapped into low dimensional eigen space : the Emotion space, and estimation is achieved by projecting input images on to the Emotion Space. In this paper we have constructed three kinds of expression models : happiness, anger, surprise, and experimental results are evaluated. Using our method, we realize an interactive system : the Facial Expressiz Video controller, which can control a video playing by the recognition results, and indicates the usefulness of our method.
抄録全体を表示