期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2014
卷号：7
期号：1
页码：9-14
出版社：Oriental Scientific Publishing Company
摘要：The paper introduces a face recognition method using probabilistic subspaces analysison multi-module singular value features of face images. Singular value vector of a face image isvalid feature for identification. But the recognition rate is low when only one module singular valuevector is used for face recognition. To improve the recognition rate, many sub-images are obtainedwhen the face image is divided in different ways, with all singular values of each image used as anew sample vector of the face image. These multi-module singular value vectors include allfeatures of a face image from local to the whole, so more discriminator information for facerecognition is obtained. Subsequently, probabilistic subspaces analysis is used under these multi-module singular value vectors. The experimental results demonstrate that the method is obviouslysuperior to corresponding algorithms and the recognition rate is respectively 97.5% and 99.5% inORL and CAS-PEAL-R1human face image databases
关键词：Face recognition; Probabilistic subspaces analysis;Multi-module; singular value decomposition
