Facial expression recognition based on wavelet transform and MLP neural network

In this paper, we proposed an algorithm for facial expression recognition based on wavelet transform and SOM and MLP neural network. The algorithm first uses discrete wavelet transform to extract feature vectors and then uses SOM neural network to further reduce data dimension. After that, An MLP neural network is used as a facial expression classifier. In the end, some experiment results are given to show the performance of the proposed.