Abstract
Facial emotion recognition is important in many academic and industrial applications. In this paper, our team proposed a novel facial emotion recognition method. First, we used discrete wavelet transform to extract wavelet coefficients from facial images. Second, principal component analysis was utilized to reduce the features. Third, a single-hidden-layer neural network was used as the classifier. Finally and most importantly, we introduced the cat swarm optimization to train the weights and biases of the classifier. The ten-fold stratified cross validation showed cat swarm optimization method achieved an overall accuracy of 89.49 +/- 0.76%. It was better than genetic algorithm, particle swarm optimization, and time-varying-acceleration-coefficient particle swarm optimization. Besides, our facial emotion recognition system was better than two state-of-the-art approaches.