Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition

TLDR

The paper proposes a novel Gabor‑Fisher classifier that augments Gabor wavelet features, reduces dimensionality with an enhanced Fisher linear discriminant, and is designed for multi‑class face recognition. The classifier extracts Gabor wavelet features, augments them, applies the enhanced Fisher linear discriminant for dimensionality reduction, and is evaluated against several baseline face‑recognition schemes. On the FERET dataset of 600 frontal images from 200 subjects, the GFC method achieved 100 % accuracy using only 62 features.

Abstract

This paper introduces a novel Gabor-Fisher (1936) classifier (GFC) for face recognition. The GFC method, which is robust to changes in illumination and facial expression, applies the enhanced Fisher linear discriminant model (EFM) to an augmented Gabor feature vector derived from the Gabor wavelet representation of face images. The novelty of this paper comes from (1) the derivation of an augmented Gabor feature vector, whose dimensionality is further reduced using the EFM by considering both data compression and recognition (generalization) performance; (2) the development of a Gabor-Fisher classifier for multi-class problems; and (3) extensive performance evaluation studies. In particular, we performed comparative studies of different similarity measures applied to various classifiers. We also performed comparative experimental studies of various face recognition schemes, including our novel GFC method, the Gabor wavelet method, the eigenfaces method, the Fisherfaces method, the EFM method, the combination of Gabor and the eigenfaces method, and the combination of Gabor and the Fisherfaces method. The feasibility of the new GFC method has been successfully tested on face recognition using 600 FERET frontal face images corresponding to 200 subjects, which were acquired under variable illumination and facial expressions. The novel GFC method achieves 100% accuracy on face recognition using only 62 features.