基于局部奇异值分解和模糊决策的人脸识别方法

Face Recognition Method Based on Singular Value Decomposition and Fuzzy Decision

针对仅在整幅人脸图像上进行奇异值分解无法得到人脸识别所需的足够信息的特点,提出了一种利用人脸图像的局部奇异值和模糊决策进行人脸识别的方法。该方法的关键是不在整幅人脸图像上进行,而是在人脸的不同区域进行奇异值分解以提取更丰富的信息。提出了人脸局部奇异值特征向量的构造方法。在识别阶段,对待识别人脸的特征向量,计算其对各人脸样本的隶属度,最后做出判断。该方法与传统方法在ORL人脸库上进行的对比实验结果表明了该方法的优越性。

A face recognition method using singular value decomposition （SVD） on human local facial area and fuzzy decision is presented in this paper to solve the problem that singular value decomposition on whole facial image can not provide enough information for face recognition. The key of this approach is that singular value decomposition is applied to different parts of human facial area instead of the whole facial region. So the rich information can be obtained for recognizing human face. The way of establishing feature vectors based on local singular value decomposition is proposed. In the recognition step, the features vector of input facial image are set up, and then the membership degrees of these features to each facial sample are computed respectively, and finally the decision can be obtained. Comparative experimental results on ORL face database show that its performance is better than that of traditional SVD-based methods.