Abstract
Commercial iris biometric systems exhibit good performance for near-infrared (NIR) images but poor performance for visible wavelength (VW) data. To address this problem, we propose an iris biometric system for VW data. The system includes localizing iris boundaries that use bimodal thresholding, Euclidean distance transform (EDT), and a circular pixel counting scheme (CPCS). Eyelids are localized using a parabolic pixel counting scheme (PPCS), and eyelashes, light reflections, and skin parts are adaptively detected using image intensity. Features are extracted using the log Gabor filter, and finally, matching is performed using Hamming distance (HD). The experimental results on UBIRIS and CASIA show that the proposed technique outperforms contemporary approaches.