A fast iris localization using inversion transform and restricted circular Hough transform

This paper presents a fast segmentation of iris portion from an eye image in an iris recognition system. In iris segmentation, we have to find the inner boundary (between pupil and iris) and outer boundary (between sclera and iris). To find the inner boundary a restricted circular Hough transform based method is applied. To locate the outer boundary image is first passes through inversion transform and then restricted circular Hough transform method is used. Both restricted circular hough transform method and inversion transform reduce the search space of the Circular Hough transform. The proposed method is a faster one and gives a high accuracy result. The performance of the proposed method is tested with three standard iris databases MMU1, CASIA-Iris V3 and IITD.