Partial segmentation and matching technique for Iris recognition

Abstract

One of the main issues in iris segmentation is that the upper and lower region of the iris is occluded by the eyelashes and eyelids. In this paper, an effort has been made to solve the above problem. The pupil boundary is detected using adaptive thresholding and circular hough transform (CHT). The iris boundary is detected by drawing arcs of different radius from the pupil center and finding maximum change in intensity. The annular region between the iris inner and outer boundary is partially segmented. The segmented iris is transformed into adaptive rectangular size strip. Features are extracted using scale-invariant feature transform (SIFT). The experimental results show that the proposed technique has achieved high accuracy and low error rate.