Segmentation based background removal technique for enhanced Iris recognition

Iris based authentication is a pattern recognition technique that makes use of Iris patterns, which are analytically unique. In this paper, we propose a novel approach for enhanced Iris Recognition (IR) system using Segmentation based Background Removal (SBR) and Triangular shaped DCT (TriDCT) extraction techniques. Segmentation is a process of isolating the objects of interest from the rest of scene. SBR is used to extract the prominent Iris portion from the eye image using Circular Hough Transform (CHT). TriDCT helps in extracting reduced set of feature vector. A Binary Particle Swarm Optimization (BPSO) based feature selection algorithm is used to search the feature space for optimal feature subset. The experiments performed on MMU and IITD iris databases show significant increase in recognition rate. Our results justify the effectiveness of the proposed technique.