Gabor-based Face Recognition Under Varying Pose and Expression Using PCA plus LDA

Abstract

Abstrak – A pose and expression robust Gaborbased face recognition method is proposed in this paper. This involves convolving a face image with a series of Gabor wavelets at different scales, locations, and orientations. Linear Subspace methods such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are then applied to the feature vectors for dimension reduction as well as class separability enhancement. A database of 400 frontal-view face images from the ORL face database is used to test the method. Experimental results show that the method is effective for both dimension reduction and good recognition performance in comparison with traditional entire Gabor filter bank. The best rank 1 recognition rate achieves 96% when the training images per individual is 5 and the number of eigenvectors-used is 60% .

Topics

7 Figures and Tables

Download Full PDF Version (Non-Commercial Use)