A New Approach for Non-Ideal Iris Segmentation Using Fuzzy C-Means Clustering Based on Particle Swarm OptimizationAuthor : Satish Rapaka, Rajeshkumar Pullakura and Jeevan Mandelli
Volume 7 No.2 July-December 2018 pp 42-45
Segmentation is an important step in iris recognition system because the accuracy of the iris recognition system is affected by the segmentation of the iris. In this paper, an efficient method has been proposed for the segmentation of non-ideal iris images captured under uncooperative conditions. A fuzzy c-means clustering algorithm based on Particle Swarm Optimization (PSO) technique has been employed as a pre-segmentation step in the iris recognition framework. The fuzzy c-means clustering method delimits the iris and eliminates the unwanted portions of an image. The particle swarm optimization technique is incorporated to avoid FCM fall into local minimum. The segmentation accuracy of the proposed method is implemented by considering CASIA v3 Interval and UBIRIS databases. The proposed method is compared with the classical segmentation methods and has an encouraging performance.
Geodesic Active Contours (GACs), Fuzzy C-Means, Particle Swarm Optimization (PSO), Iris Recognition System
 F. G. Adler, “Physiology of the eye”,Mosby, Chapter VI, pp. 143, 1953.
 J.H. Doggart, “Ocular Signs in Slit-Lamp Microscopy”,Kimpton, pp. 27, 1949.
 J. Daugman, “How Iris Recognition Works”, Essent. Guid. to Image Process., Vol. 14, No. 1, pp. 715-739, 2009.
 R. P. Wildes, “Iris recognition, an emerging biometric technology’Proc. IEEE, 1997, Vol. 85, No. 9, pp. 1348-1363.
 L. Masek andP. Kovesi, “A Biometric Identification System Based on Iris Patterns’the school of Computer Science and Software Engineering, The University of Western Australia, 2003.
 K. Miyazawa, K. Ito, T. Aoki, K. Kobayashi andH. Nakajima, “An effective approach for Iris recognition using phase-based image matching”, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 30, No. 10, pp. 1741-1756, 2008.
 L. Ma, Y. Wang, T. Tan, “Iris recognition using circular symmetric filters”, Object Recognit. Support. by user Interact. Serv. Robot., Vol. 2, pp. 414-417, 2002.
 A. Bouaziz, A. Draa andS. Chikhi, “Artificial bees for multilevel thresholding of iris images”, Swarm Evol. Comput., Vol. 21, pp. 32-40, 2015.
 J. Daugman, “New methods in iris recognition.”, IEEE Trans. Syst. Man. Cybern. B. Cybern., Vol. 37, No. 5, pp. 1167-1175, 2007.
 K. Roy, P. Bhattacharya andC. Y. Suen, “Towards nonideal iris recognition based on level set method, genetic algorithms and adaptive asymmetrical SVMs”, Eng. Appl. Artif. Intell., Vol. 24, No. 3, pp. 458-475, 2011.
 D. S. Jeong andJ. W. Hwang and B. J. Kang, et al., “A new iris segmentation method for non-ideal iris images”, Image Vis. Comput., Vol. 28, No. 2, pp. 254-260, 2010.
 S. Shah and A. Ross, “Iris segmentation using geodesic active contours”, Inf. Forensics Secur. IEEE Trans., Vol. 4, No. 4, pp. 824-836, 2009.
 V. Caselles, R. Kimmel andG. Sapiro, “Geodesic Active Contours”, IEEE Int”, l Conf. Comput. Vis., Vol. 22, No. 1, pp. 694-699, 1995.
 M. Kass, A. Witkin andD. Terzopoulos, “Snakes, Active contour model”, Int. Journ. of Comput. Vision, pp. 321-331, 1998.
 S. Kichenassamy, A. Kumar, , P. Olver, A. Tannenbaum and A. Yezzi, , “Gradient flows and geometric active contour models”, Proc. IEEE Int. Conf. Comput. Vis., pp. 4-9, 1995.
 Cannon, R.L., Dave, J. V, Bezdek, J.C., “Efficient Implementation of the Fuzzy c-Means Clustering Algorithms”, IEEE Trans. Pattern Anal. Mach. Intell.,Vol. 8, No. 2, pp. 248-255, 1986.
 R. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory”, Proc. Sixth Int. Symp. Micro Mach. Hum. Sci., pp. 39-43, 1995.
 S. Rapaka andP. R. Kumar, “Efficient approach for non-ideal iris segmentation using improved particle swarm Q1 optimisation-based multilevel thresholding and geodesic active contours”, pp. 1-9, 2018. [Online] Available: https://doi.org/10.1049/iet-ipr.2016.0917.