This paper proposes a novel algorithm to improve localization and segmentation of an iris image. Since in many practical applications, user cooperation is not possible, eyelash occlusion can seriously affect the performance of an iris recognition system. This paper discusses a robust method for accurate localization and segmentation of the exact iris region without eyelash occlusion. Our algorithm uses a logarithmic image enhancement technique and the Hough transform for iris localization as well as an intensity gradient based method for eyelash detection using local region statistics of the image. Experimental results show the accuracy of our algorithm leading to exact iris region segmentation.
24th Biennial Symposium on Communications, BSC 2008
Carleton University

Youmaran, R. (Richard), Xie, L.P., & Adler, A. (2008). Improved identification of iris and eyelash features. Presented at the 24th Biennial Symposium on Communications, BSC 2008. doi:10.1109/BSC.2008.4563282