Comparative Study of Different Iris Occlusion Estimation Techniques

Abstract

The work presented in this paper involve developing an iris recognition system in order to verify both uniqueness of the human iris and also its performance as a biometric. The recognition system consist of automated segmented stage based on Hough transform and is able to localize the circular iris and pupil region, occluding eyelids and eyelashes, reflections. The extracted iris region was then normalized into rectangular block of constant dimension to account for imaging inconsistencies. Three comparative systems based on phase, mean and LBP are studied in this paper.