外文翻译原文-智能安防人脸识别系统研究与开发.pdfVIP

S c i e n t i f i c I m a g e P r o c e s s i n g Improving Face Recognition Performance Using RBPCA MaxLike and Information Fusion Face recognition is typically an ill-posed problem because of the limited number of available samples. As experimental results show, combining multiclassifier fusion with the RBPCA MaxLike approach, which couples covariance matrix regularization and block- based principal component analysis (BPCA), can provide an effective framework for face recognition that alleviates the small sample size problem. ith the advent of biometric sys- regularization, block-based principal component tems, the human face has been analysis (BPCA), and maximum-likelihood clas- widely exploited in security and sification.4 To our knowledge, this is the first time W surveillance applications. One of researchers have combined RBPCA MaxLike and the most challenging tasks in biometrics is human- information-fusion methods to solve a face recog- face recognition, which consists of linking an nition problem. input face with an individual entry in a database Our motivation is to develop a novel classifica- of known persons. The face recognition process tion system for face recognition by performing a involves two main steps: feature extraction and statistical modeling of human face images. The feature classification, which includes holistic, main goal is to achieve supervised parametric 1 feature-based, an