Fuzzy Rule Based Facial Expression Recognition

Facial expressions are a key modality in human communication. Facial expressions occur simultaneously with social interaction and help in interpretation of spoken communication. The understanding of facial expressions is a basic requirement in the development of next generation human computer interaction (HCI) systems. Facial expressions, however, are qualitative in nature and it is very difficult to explain them by a mathematical model. This paper presents a system framework that uses fuzzy logic principles to recognize facial expressions in video sequences. The system uses image processing techniques to detect MPEG4 facial animation parameters (FAPs) in an input video. A fuzzy rule base has been developed to interpret the collective set of FAPs as constituting a particular facial expression.