Facial Expression Recognition in Video using Adaboost and SVM

In human-computer interaction facial expression is the characteristic and proficient method for correspondence, and has been acknowledged as essential input of such interface. In this paper, we present an enhancement in facial expression recognition for image sequence. The most important step is to extract essential features from face to efficiently determine facial expression. Experimentation shows that LBP method performs well while extracting facial features. We further found that Boosted-LBP extracts most distinct features and the best recognition is calculated by SVM classifier.