12-7 Comparison of Facial Expression Recognition Rates Depending on Combination of Different Facial Regions

Abstract

This work presents a facial expression recognition algorithm based on segmentation of a face image into four facial regions (forehead, eyes, nose and mouth) in order to compare recognition rates using one region and all possible combinations of four facial regions. In feature extraction stage the proposed method employs Sub-block Eigenphases algorithm that uses Principal Component Analysis (PCA) and for classification stage it applies the Support Vector Machine (SVM).