A Facial Expression Model for Human-Like Agent

A major unsolved problem in human-like agent is the construction and application of realistic human facial expression models. Human-like agents should interact with human by recognizing human facial expression and synthesizing facial expressions to show their emotional states. However there is no a uniform model for both recognition and synthesis of facial expression. In this paper, we present a model for solving this challenging task. First, we setup a muscle-based facial model and use muscles´ contraction as controlling factors because all the facial actions are driven by the muscles. An orthogonal facial expression space is constructed by regarding each controlling factor as a dimension. Then muscles´ contractions are calculated from facial images to construct the facial vector. Thus the facial vector can be used on the facial expression synthesis system of human-like agent. In this paper, we also present a facial function to describe the dynamic procedure of facial expressions. Last, this paper points out the direction of future work