Facial expression recognition using Support Vector Machines

This paper propose a facial expression recognition approach based on Principal Component Analysis (PCA) and Local Binary Pattern (LBP) algorithms. Experiments were carried out on the Japanese Female Facial Expression (JAFFE) database and our recently introduced Mevlana University Facial Expression (MUFE) database. Support Vector Machine (SVM) was used as classifier. In all conducted experiments on JAFFE and MUFE databases, obtained results reveal that PCA+SVM has an average recognition rate of 87% and 77%, respectively.