Facial expression recognition using Stochastic Neighbor Embedding and SVMs
Mingwei Huang, Zhen Wang, Zilu Ying · 2011
Facial expression recognition (FER) has become a hot topic in the computer vision and pattern recognition communities because of its great potential applications in many areas such as human computer nature interaction, animation etc.. In this paper, we present a new approach to facial expression recognition, which uses Stochastic Neighbor Embedding (SNE) for reducing the high dimensional data of facial expression images into a relatively low dimension data and then uses support vector machine (SVM) as the classifier for the expression classification afterwards. The proposed new algorithm is applied to facial expression recognition on Japanese Female Facial Expression (JAFFE) database, better performance is gained compared with those traditional algorithms, such as PCA and LDA etc.. The results have further proved the effectiveness of our proposed algorithm.