关键词: 表情识别, 特征融合, 局部二值模式, 离散余弦变换

Abstract: In order to effectively extract facial expression feature, a novel method by fusing Discrete Cosine Transform（DCT） and Local Binary Pattern（LBP） features is proposed for expression recognition in this research. The primary information of the face image is centralized in a small number of DCT coefficients, which are used as the global feature of the expression. The face is divided regularly into small regions, from which LBP histograms are computed and concatenated into a LBP features. Subsequently, weight fusion operation is done on these results that are gotten and the nearest distance classification is used to distinguish each testing expression sample. The experiments on JAFFE and Cohn-Kanade expression database show the method proposed is more effective to represent facial expression feature than the single LBP or DCT feature.

Key words: expression recognition, feature fusion, Local Binary Pattern（LBP）, Discrete Cosine Transform（DCT）