Facial Expression Recognition using AAM and Local Facial Features

A new technique for facial expression recognition is proposed, which uses active appearance model (AAM) to extract facial feature points and combines useful local shape features to form a classifier. To enhance performance of AAM, we use Adaboost to locate eye position to initialize AAM. After extraction of facial feature points, we analyze local facial changes and use some simple features to form an effective classifier. At last, we demonstrate our approach by experiments.