Skip to Main Content
A feature fusion algorithm with application to facial expression recognition is presented. Firstly, the brows, eyes and mouth areas are segmented from the facial expression images, and are computed with Higher-order Local Auto-Correlation (HLAC) method, and the Weighted Principal Component Analysis (WPCA) is used to reduce dimensions secondly, in which the weights values are obtained according to facial expression measure system Face Action Coding System (FACS) in psychology. And finally minimum-distance classifier is used to recognize different expressions. Based on the CMU-PITTSBURGH AU-Coded Face Expression Image Database, the results show that the features fusing method is superior to PCA-based method.