Research On The Technique Of Face Recognition

Face Recognition is a user-friendly technique for personal identification, which is regarded as an important direction of biometric recognition techniques. It is a complex and difficult problem that is important for surveillance and security, telecommunications, digital libraries, video meeting, and human-computer intelligent interactions. Despite the fact that human faces are essentially similar, we are very skilled at recognizing the identities of people from their faces. We can perform this task very easily and it is a basic and important social act although we are still puzzled with the psychological and physiological nature of the process.Three major procedures in FR are presented in the research: normalization, feature extraction, classifier design, Based on the AR face database provided by the face recognition research group of Purdue University, five kinds of face features, including PCA features, KPCA features, R-LDA features, KDDA features and central moment features, are extracted. The recognition performances of these features are tested by using minimum Euclidean distance and support vector machine (SVM) classifiers. The experimental results show that the KDDA features achieve the best recognition performance, and the SVM classifier outperforms the minimum Euclidean distance classifier.