Facial Expression Recognition Based on Fusion of Multiple Gabor Features

In order to accomplish subject-independent facial expression recognition task, a multiple Gabor features based facial expression recognition method is presented in this paper. Different channels of Gabor filters have different contributions on the facial expression recognition and reasonable combination of these features can improve the performance of a facial expression recognition system. NN based data fusion method is designed for facial expression recognition in this paper. Experimental results show that the facial expression recognition rate can be improved by using multiple channel features and neural network fusion