A Novel Circle Detection Method for Iris Segmentation

This paper introduces a novel approach for iris segmentation. In detecting the inner boundary of the iris, the method introduces a circular filter which is specially designed to detect circular shapes in images. The inner boundary detection process consists of two steps. Firstly, a coarse circle of the pupil is detected by the proposed circular filter after a binarization to the input iris image. Then, the inner boundary is accurately located by applying a modified circular Hough transform in an extracted region from the coarse center. The presented method further proposes a process of extracting the outer boundary of the iris by applying a linear filter to the rectangular areas transformed from arc regions around the iris. Experimental results show promising performances on iris images captured in ideal and non-ideal conditions from the CASIA iris database version 1 and 2.