Compare Gabor Fisher Classifier and Phase-Based Gabor Fisher Classifier for Face Recognition

Abstract

The paper compares two feature extraction techniques for face recognition with Gabor Filters. Firstly Gabor Filters based methods which mainly use only Gabor magnitude features like Gabor Fisher Classifier (GFC), and secondly the proposed method called the Phase-based Gabor Fisher Classifier (PBGFC) by turk[3]. The PBGFC method constructs an augmented feature vector which encompasses Gabor-phase information derived from a novel representation of face images - the oriented Gabor phase congruency image (OGPCI) - and then applies linear discriminant analysis to the augmented feature vector to reduce its dimensionality. In ours experiments we use the ORL data base, the feasibility of the proposed methods was assessed in a series of face verification experiments. The experimental results show that the PBGFC method performs better than other popular feature extraction techniques such as (LDA), while it ensures nearly similar verification performance as the established Gabor Fisher Classifier (GFC).