关键词: 显著图, 结构张量特征, 局部二值模式（LBP）特征, 自适应加权

Abstract: Aiming at the problem that Local Binary Pattern（LBP） algorithm ignores the local structure information when extracting texture features, a novel expression recognition algorithm by adaptive weighted fusion of salient structure tensor and LBP feature is proposed. The method first eliminates fine textures and noises by detecting the salient regions on the entire image to obtain a global salient map. Second, salient texture features are further extracted based on the salient map. According to the contribution of each feature information entropy, the feature vector is weighted. Finally, the Support Vector Machine（SVM） is used to classify the expression images. The experimental results show that the two texture features of adaptive weighted fusion can better describe the features of human face and effectively improve the expression recognition rate.

Key words: salient map, structure tensor feature, Local Binary Pattern（LBP） feature, adaptive weighted