Enhancement of Neuro-eigenspace Face Recognition Using Photometric Normalization

Abstract

A face recognition system based on recent method which concerned with both representation and recognition using learning algorithm is presented. The learning algorithm, artificial neural network is used as a classifier for face recognition and face verification whereas the features are extracted using linear sub- space techniques. This paper initially provides the overview of the proposed face recognition system, and explains the methodology used. It then explains the performance evaluation of the proposed system by applying two photometric normalization techniques: Histogram equalization and Homomorphic filtering, and comparing with Euclidean distance and normalized correlation classifiers. The system produces promising results for face verification and face recognition where it achieved false acceptance rate (FAR) of 2.98% and false rejection rate (FRR) of 2.59% using ANN classifier with PCA feature extraction using homomorphic filtering, and 94.4% for recognition.