Facial expression imitation for human robot interaction

Abstract

As social robots become more and more interactive and communicated, it is crucialthat they can understand, perceive and imitate the human emotions appropriatelyin the social environment. We propose an interactive system consisting of two keycomponents, facial expression recognition and robot imitation. Within the recentdecade, facial expression recognition has become a hot topic. But the existing 3Dface mesh for facial expression recognition is based on the assumption of linearmass-spring model which can not simulate the facial muscle movements e ectively.Thus in the system,a nonlinear mass-spring model is employed to simulate twentytwo facial muscles' tensions during facial expressions, and then the elastic forcesof these tensions are grouped into a vector which is used as the input for facialexpression recognition. The experimental results show that the nonlinear facialmass-spring model coupled with the MLPs classi er is e ective to recognize thefacial expressions. For the robot imitation, we introduce the mechanism of ourrobot on imitating the facial expressions. Experimental results of imitating facialexpressions demonstrate that our robot can imitate six kinds of facial expressionse ectively.