EXPERIMENTAL RESULTS

In this section, we evaluate the performance of PCA, LDA, KPCA, KLDA, RDCT and RDWT algorithms using three databases: (1) Face Recognition Technology (FERET), (2) an Olivetti Research Laboratory (ORL), and (3) Yale. In the first part of this section, we have briefly described the databases, the characteristics of the images and the normalization procedure. This is followed by the experiments carried out.

Databases and Normalization Procedure

The FERET database, which has become the de facto standard for evaluating the face recognition technologies, consists of more than 13,000 facial images corresponding to more than 1500 subjects. The diversity of the FERET database is across gender, ethnicity, and age. Since images are acquired during different photo sessions, the illumination conditions, facial expressions, and the size of the faces have been varied. The data set used in our experiments consists of 2500 gray frontal FERET face images (normal, varying illumination and varying facial expressions) corresponding to 300 subjects. The images are of size 256 X 384 with 8-bit resolution. The normalization process detects the center of the eyes and crops the image to the size of 128 X 128 (Phillips 2000). The normalized images (from FERET database) used in following experiments are shown in Figure 5.