Facial Feature based Expression Recognition for an Affective Interface

F. Ren, N. Nagano, D.B. Bracewell, S. Kuroiwa, T. Tanioka, Z. Zhang (Japan), and C. Zong (PRC)


Affective Computing, Expression Recognition, Emotion Recognition


We focus on human psychological characteristics to de velop general-purpose agents that can recognize human emotion and create machine emotion. In this paper a sys tem for identifying facial expressions by using facial fea tures is presented. The system recognizes 7 facial expres sions. The 7 facial expressions are made up of 6 basic emotional expressions (happiness, sadness, surprise, fear, anger, and dislike) and one non-expression. The Facial Ac tion Coding System (FACS) is used to make the resulting system robust. For identification, the shortest distance be tween the input features and features stored in a dictionary is used. From these facial expressions a user’s intention can be extrapolated and used to improve the human computer interaction experience.

Important Links:

Go Back