Face recognition using fisher linear discriminant analysis and support vector machine

Abstract

A new face recognition method is presented based on Fisher's Linear Discriminant Analysis (FLDA) and Support Vector Machine (SVM). The FLDA projects the high dimensional image space into a relatively low-dimensional space to acquire most discriminant features among the different classes. Recently, SVM has been used as a new technique for pattern classification and recognition. We have used SVM as a classifier, which classifies the face images based on the extracted features. We have tested the potential of SVM on the ORL face database. The experimental results show that the proposed method provides higher recognition rates compared to some other existing methods. © 2009 Springer Berlin Heidelberg.