Efficient Iris Recognition System Using Robust Iris Segmentation and Hybrid Feature Extraction Methods

Ms. Rasika P. Rahane, Prof. Deepak Gupta


The iris recognition is playing significant role in human identification, efficiency in terms of accuracy and processing time is very important for such systems. In literature number of methods are presented for iris recognition based on iris segmentation, feature extraction and classification methods. There are number of drawbacks reported for such methods. In this Paper, we are designing novel framework for iris recognition based robust iris segmentation method, hybrid feature extraction method and feed forward neural network (FFNN) classifier. In this paper, novel iris segmentation technique is presenting for non-ideal iris images. This method is based on two techniques for pupil segmentation, and then fusion of expanding and shrinking active contour is designed for the segmentation of iris by combining the novel pressure force to active contour model. Then to effectively un wrap the segmented iris, proposing non-circular iris normalization method. After the efficient iris segmentation, we are applying the proposed feature extraction technique in which 2D-DWT (Discrete Wavelet Transform), texture features and geometric features of segmented iris image are used. The features extracted are combined together to from the hybrid feature vector. For recognition purpose we are using FFNN

Full Text:



J. G. Daugman, High confidence visual recognition of persons by a test

of statistical independence, IEEE Trans. Pattern Anal. Mach. Intell., vol.

, no. 11, pp. 11481161, Nov. 1993.

R. P. Wildes, Iris recognition: An emerging biometric technology, Proc.

IEEE, vol. 85, no. 9, pp. 13481363, Sep. 1997.

Y. Zhu, T. Tan, and Y. Wang, Biometric personal identification based on

iris patterns, in Proc. 15th Int. Conf. Pattern Recognit., vol. 2. Barcelona,

Spain, 2000, pp. 801804.

Z. Z. Abidin, M. Manaf, and A. S. Shibghatullah, Iris segmentation

analysis using integro-differential and hough transform in biometric

system, J. Telecommun. Electron. Comput. Eng., vol. 4, no. 2, pp. 4148,

J. Huang, X. You, Y. Y. Tang, L. Du, and Y. Yuan, A novel iris

segmentation using radial-suppression edge detection, Signal Process.,

vol. 89, no. 12, pp. 26302643, 2009.

H. Proenca and L. A. Alexandre, A method for the identification of

inaccuracies in pupil segmentation, in Proc. 1st Int. Conf. Availability

Rel. Security. (ARES), Vienna, Austria, 2006, pp. 15.

M. Haidekker, Deformable Models and Active Contours. Canada: Wiley,

, pp. 173210.

M. Kass, A. Witkin, and D. Terzopoulos, Snakes: Active contour models,

Int. J. Comput. Vis., vol. 1, no. 4, pp. 321331, 1988.

C. Xu and J. L. Prince, Snakes, shapes, and gradient vector flow, IEEE

Trans. Image Process., vol. 7, no. 3, pp. 359369, Mar. 1998.

L. D. Cohen and I. Cohen, Finite-element methods for active contour

models and balloons for 2-D and 3-D images, IEEE Trans. Pattern Anal.

Mach. Intell., vol. 15, no. 11, pp. 11311147, Nov. 1993.


Copyright © IJETT, International Journal on Emerging Trends in Technology