一种个体特征脸子空间与奇异值相结合的人脸验证算法

Face Verification Based on Combination of Individual Eigenface Subspace and SVD

提出了一种个体特征脸子空间与奇异值特征相结合的人脸验证方法。该方法首先利用小波变换减小表情因素对人脸验证的影响,再为每个人建立单独的个体特征脸子空间。验证时,将测试人脸投影到训练样本的特征脸子空间上,然后利用样本特征脸子空间的奇异值特征矢量在欧氏距离上进行验证。本文为ORL人脸数据库制定了实验协议,并在此基础上进行了测试,取得了较好的结果。

An approach to face verification based on the integration of individual eigenface subspace and SVD is presented in which the wavelet transform is used to reduce the effect of expression on the face verification.An individual specific face subspace for each person is established in frequency space. An image of test face is projected to the individual face subspace.SVD vectors in the individual face subspace are computed in Euclidean distance for face verification.Experimental protocol is defined for ORL face database.Good results are obtained through the experiments and conducted to the ORL face image database.