A New Approach for Non-Ideal Iris Segmentation Using Fuzzy C-Means Clustering Based on Particle Swarm Optimization
DOI:
https://doi.org/10.51983/ajeat-2018.7.2.1009Keywords:
Geodesic Active Contours (GACs), Fuzzy C-Means, Particle Swarm Optimization (PSO), Iris Recognition SystemAbstract
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.
References
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, vol. 85, no. 9, pp. 1348-1363, 1997.
L. Masek and P. Kovesi, "A Biometric Identification System Based on Iris Patterns", The University of Western Australia, School of Computer Science and Software Engineering, 2003.
K. Miyazawa et al., "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 and S. 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 and C. 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 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 and G. Sapiro, "Geodesic Active Contours", IEEE Int'l Conf. Comput. Vis., vol. 22, no. 1, pp. 694-699, 1995.
M. Kass, A. Witkin and D. Terzopoulos, "Snakes, Active contour model", Int. Journ. of Comput. Vision, pp. 321-331, 1998.
S. Kichenassamy et al., "Gradient flows and geometric active contour models", Proc. IEEE Int. Conf. Comput. Vis., pp. 4-9, 1995.
R. L. Cannon, J. V. Dave and J. C. Bezdek, "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 and P. R. Kumar, "Efficient approach for non-ideal iris segmentation using improved particle swarm optimization-based multilevel thresholding and geodesic active contours", pp. 1-9, 2018. [Online]. Available: https://doi.org/10.1049/iet-ipr.2016.0917.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2018 The Research Publication
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
