Optimized Daugman’s algorithm for iris localization

Abstract

Iris localization is considered the most difficult part in iris identification algorithms because it defines the inner and outer boundaries of iris region used for feature analysis. Several researches were made in the subject of iris finding and segmentation. The main objective here is to remove any non-useful information, namely the pupil segment and the part outside the iris (sclera, eyelids, skin). R. Wildes used Hough transforms to detect the iris contour. Daugman proposed an integro-differential operator to find both the pupil and the iris contour. Daugman’s method is claimed to be the most efficient one. This paper proposes an implementation for Daugman's algorithm, which was found incompatible with visible light illuminated images. Then this paper proposes new algorithm for solving this problem.