Face Recognition Using Principal Component Analysis and Linear Discriminant Analysis on Holistic Approach in Facial Images Database

Abstract

Face recognition system should be able to automatically detect a face in images. This involves extraction of its features and then recognizes it, regardless of lighting, ageing, occlusion, expression, illumination and pose. Principal component analysis and linear discriminant analysis are tested and compared for the face recognition of facial images database. In present paper we have attempted a comparative study of principal component analysis and linear discriminant analysis. The first experiment is used standard face 95 database, local database and pose variation database. The performance of PCA is 100%.The second experiment uses standard Grimance database. The success rate of classification of images is 100%. The value of projection vectors is 0.0076, 0.0056, 0.0008, 0.0036 and 0.0028. The graph shows the LDA projection vector, eigenvalues and eigenvectors of these images.