Shape analysis using generalized procrustes analysis on Active Appearance Model for facial expression recognition

Facial expression recognition is an active research area in the field of signal social processing. The goal is to distinguish human emotion. The problem is similar emotion, variation of emotion, and independent object through face image. The existing research using various method for modeling human facial to entirely describe facial expression through face image. We consider to variation analysis of the face image using Generalized Procrustes Analysis (GPA) method. GPA is implied for modeling variation of facial expression. We fit our GPA model exact the position of facial skeleton using Active Appearance Model (AAM). AAM is needed for extract shape feature of face image. Also, we use Gabor to get texture information of face image. The facial expression recognition method is based on Support Vector Machine (SVM). We tested our model with CK+ and Jaffe dataset on six basic emotion: anger, disgust, fear, happy, sad, and surprise. Our method gained accuracy 93.58% for CK+ dataset and 94.7% for Jaffe dataset.