An improved fast algorithm of iris localization

Abstract

The iris, an annulus region where located in the area between the pupil and sclera, its unique texture almost never changes in whole life. Iris location is to locate the effective region and prevent interference with the invalid region. Iris localization is an important part in the Iris recognition system, accuracy and speed of the positioning directly affects the performance of iris recognition system. On the basis of existing analysis on iris recognition algorithms, dividing the positioning process into two steps: the rough positioning and the precise positioning. In the first step, based on gray window, which can reduce the specifically searching range and can avoid the eyelash, eyelids and the disturbance of external spotlight source effectively, etc., we introduce a new method that estimates coarse positioning of pupil center. In the step of fine positioning, based on Canny edge detection algorithm and the Hough transform, we introduce an improved algorithm. In the process of Edge extraction, utilizing the feature between internal and outer edges and the Hough transform, we adjust the size of extracted image block, a small image would be fixed the size due to the prior experimental results. Experimental results show that the localization algorithm ensure the accuracy of iris localization while enhancing the localization speed. Effectively overcome the serious influence of eyelids and eyelashes. In conclusion, The Improved Iris Location Algorithm is feasible.