Real-Time Capable Method for Facial Expression Recognition in Color and Stereo Vision

摘要: In this paper we present a user independent real-time capable automatic method for recognition of facial expressions related to basic emotions from stereo image sequences. The automatically detects faces in unconstraint pose based on depth and color information. order overcome difficulties caused by increasing change pose, lighting transitions, or complicated background, introduce face normalization algorithm an Iterative Closest Point algorithm. normalized images defined set physiologically motivated regions subset muscles which are apt detect the six well-known basis emotions. Visual expression analysis takes place optical flow feature extraction nearest neighbor classification, uses distance measure, i.e. current vector pattern is matched against empirically determined ground truth data.