"Performance Analysis on Half Iris Feature Extraction using GW, LBP and HOG"

Iris recognition is the most accurate biometrics which has received increasing attention in departments which require high security. In this paper, we discussed Gabor Wavelet, Local Binary Pattern, Histogram of Oriented Gradient techniques to extract features on specific portion of the iris for improving the performance of an iris recognition system. The main aim of this paper is to show that is enough to choose the half portion of the iris to recognize authentic users and to reject imposters instead of whole extension of the iris. The proposed methods are evaluated based upon False Rejection Rate (FRR) and False Acceptance Rate (FAR) and the experimental results show that this technique produces good performance on MMU iris database.