Author : Rapaka Satish 1
Date of Publication :7th June 2015
Abstract: The stable unique epigenetic pattern of the iris make it a robust biometric trait for personal identification. The first stage of iris recognition is to isolate the actual iris region in a digital eye image. The segmentation stage is critical to the success of an iris recognition system, since data that is falsely represented as iris pattern data will corrupt the biometric templates generated, resulting in poor recognition rates. Most segmentation models in the literature assume that the pupillary, limbic, and eyelid boundaries are circular or elliptical in shape. Hence, they focus on determining model parameters that best fit these hypotheses. However, it is difficult to segment iris images acquired under non ideal conditions using such conic models. In this paper we use Geodesic Active Contours (GAC) for segmenting iris from the surrounding structures. Since active contours can 1) assumes any shape and 2) segment multiple objects simultaneously. Experimental Results on the UBIRIS and CASIA v4.0 iris databases indicate the efficacy of the proposed technique
Reference :
-
[1] F. H. Adler, Physiology of the Eye: Clinical Application (fourth edition). London: The C.V. Mosby Company, 1965.
[2] J. Daugman, “New methods in iris recognition,” IEEE Trans. Syst.,Man, Cybern., vol. 37, no. 5, pt. B, pp. 1167– 1175, 2007.
[3] J. G. Daugman, “High confidence visual recognit ion of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 15, no. 11, pp. 1148–1160, Nov. 1993.
[4] Libor Masek, Peter Kovesi. MATLAB Source Code for a Biometric Identification System Based on Iris Patterns. The School of Computer Science and Software Engineering, The University of Western Australia. 2003.
[5] A. Ross and S. Shah, “Segmenting nonideal irise s using Geodesic Active Contours,” in Proc. Biometrics Symp. (BSYM), Baltimore, MD, Sep. 2006.
[6] V. Caselles, R. Kimmel, and G. Sapiro, “Geodesi c active ontours,” Int. J. Comput. Vision, vol. 22, no. 1, pp. 61–79, Feb./Mar. 1997.
[7] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes : Active contour models,” Int. J. Comput. Vision, vol. 1, no. 4, pp. 321– 331, 1987.
[8] L. Zhukov, K. Museth, D. Breen, R. Whitaker, and A. Barr, “Level set modeling and segmentation of DT-MRI brai n data,” J. Electron. Imag.,vol. 12, no. 1, pp. 125–133, Jan. 2003.
[9] L. D. Cohen, “On active contour models and ball oons,” Comput. Vision,Graph., Image Process.: Image Understand., vol. 53, no. 2, pp.211–218, 1991.
[10] L. Masek and P. Kovesi, Matlab Source Code for Biometric Identification System Based on Iris Patterns The School of Comput. Sci.Software Eng., The Univ. Western Australia, 2003 [Online]. Available: http://www.csse.uwa.edu.au/~pk/studentprojects/libor/sourcec ode.html
[11] The CASIA Iris Image Database [Online]. Available: http://www.sinobiometrics.com