Iris recognition using radon transform thresholding based feature extraction with Gradient-based Isolation as a pre-processing technique

Iris Recognition (IR) under varying contrast and live-tissues is challenging. This paper proposes two novel techniques viz., Radon Transform Thresholding (RTT) and Gradient-based Isolation (GI). RTT is used to extract the prominent features from the pre-processed image. GI is a pre-processing technique which uses the edge detection property of Gradient operator to isolate the patterns, thereby obtaining the salient Iris textures. A Binary Particle Swarm Optimization (BPSO) based feature selection algorithm is used to search the feature vector space for the optimal feature subset. Experimental results on three benchmark Iris databases, namely, Phoenix, IITD and CASIA Iris Interval, depict promising performance of the proposed techniques for Iris recognition.