基于Gabor变换的表情识别系统的设计

针对Gabor特征维数和冗余度较高的缺点,对Gabor小波变换特征进行分块,提取了所有子块局部统计特征,然后使用PCA+LDA方法对这些特征进行选择,最后采用决策树分类法进行了人脸表情识别.实验结果表明:此方法在维数降低的同时,其识别性能比传统的方法更具优势.

Design of Facial Expression Recognition System Based on Gabor Transformation

Aiming at the deficiency of the high-dimensional and high-redundant Gabor feature vectors,firstly the Gabor wavelet coefficients are divided into blocks and the local statistical features of all Gabor wavelet representation are calculated as the feature vectors,then the sorted PCA plus LDA is used to select and compress the Gabor features,and finally a decision tree classifier is adopted to recognize facial expression.Experimental results show that the method is more effective for both dimension reduction a...