Time of Matching Reduction and I mprovement of Sub-Optimal Image Segmentation for Iris Recognition
R. M. Farouk, Gamal. F. Elhadi · 2011
In this paper, a new matching scheme based on the scalar product (SP) between two templates is used in the matching process. We also introduced the active contour technique to detect the inner boundary of the iris which is not often a circle and the circular Hough transform to determine the outer boundary of the iris. The active contour technique takes into consideration that the actual pupil boundary is near-circular contour rather than a perfect circle, which localize the inner boundary of the iris perfectly. The 1-D log-Gabor filter is used to extract real valued template for the normalized iris. We apply our system on two publicly available databases (CASIA and UBIRIS) and the numerical results show that, perfectly matching process and also the matching time is reduced. We also compare our results with previous results and find out that, the matching with SP is faster than the matching with other techniques. biometric applications include facial features, fingerprints, iris, palm-prints, retina, handwriting signature, DNA, gait, etc [17, 23]. The human iris is an annular part between pupil and sclera and its complex pattern contains many distinctive features such as arching ligaments, furrows, ridges, crypts, corona, and freckles Figure. 1. At the same time the iris is protected from the external environment behind the cornea and the eyelids. No subject to deleterious effects of aging, the small-scale radial features of the iris remain stable and fixed from about one year of age throughout one's life. The reader's two eyes, directed at this page, have identical genetics; they will likely have the same color and may well show some large scale pattern similarities; nevertheless, they have quite different iris pattern details.