Facial expression recognition based on rough set theory
基于粗糙集理论的表情识别研究

The study of human centered emotion and cognition, including affective computing and emotion recognition, is a hot research topic in artificial intelligence. In this paper, the attribute reduction algorithms were studied based on rough set theory, and it was used for feature selection of a facial emotion recognition system. Important features for emotion recognition were studied based on attribute reduction algorithms. Furthermore, a facial expression recognition method was proposed based on rough set theory plus support vector machine (SVM). Simulation results show that the attribute reduction methods of rough set can find the important features for emotion, and based on these features, the high recognition rate can be gotten.