Independent Component Analysis of Gabor Features for Facial Expression Recognition

This paper proposes a novel method for facial expression recognition by using independent component analysis of Gabor features. In the feature extraction stage, Gabor feature vectors are firstly extracted from a set of facial expressions images, then using independent component analysis (ICA) to extract the independent Gabor features. After that, the independent Gabor features are used to train SVM to realize the facial expression recognition, and the computer simulation illustrates the effectivity of this method to classify the seven expressions of the JAFFE database.