3-D Facial Expression Recognition-Synthesis on PDA Incorporating Emotional Timing

Abstract

This paper describes a pipeline by which facial expression of the face is recognized and then 3-D facial animation is synthesized in the remote place based upon timing information of the facial. The system first detects a facial area within the given image and then classifies its facial expression into 7 emotional weightings. Such weighting information, transmitted to the PDA via a mobile network, is used for non-photorealistic facial expression animation. A cartoon-like shading is used to render a 3-D avatar that conveys a familiar and yet unique facial character, even without employing extensive polygons. It turns out that facial expression animation using emotional curves is more effective in expressing the timing of an expression comparing to the linear interpolation method. The emotional avatar embedded on a mobile platform has some potential in conveying emotion between peoples in Internet.