Improving Features Subset Selection Using Genetic Algorithms for Iris Recognition

  • Kaushik Roy
  • Prabir Bhattacharya
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5064)


In this paper, we propose an iris recognition method based on genetic algorithms (GA) to select the optimal features subset. The iris data usually contains huge number of textural features and a comparatively small number of samples per subject, which make the accurate iris patterns classification challenging. Feature selection scheme is used to identify the most important and irrelevant features from extracted features set of relatively high dimension based on some selection criterions. The traditional feature selection schemes require sufficient number of samples per subject to select the most representa-tive features sequence; however, it is not always practical to accumulate a large number of samples due to some security issues. In this paper, we propose GA to improve the feature subset selection by combining valuable outcomes from multiple feature selection methods. The main objective of GA is to achieve a balance among the recognition rate, the false accept rate, the false reject rate and the selected features subset size. This paper also motivates and introduces the use of Gaussian Mixture Model for iris pattern classification. The proposed technique is computationally effective with the recognition rates of 97.81 % and 96.23% on the ICE (Iris Challenge Evaluation) and the WVU (West Virginia University) iris datasets respectively.


Biometrics Gaussian mixture model genetic algorithms collarette area localization 


  1. 1.
    Schuckers, S.A.C., Schmid, N.A., Abhyankar, A., Dorairaj, V., Boyce, C.K., Hornak, L.A.: On techniques for angle compensation in nonideal iris recognition. IEEE Trans. SMC-B 37(5), 1176–1190 (2007)Google Scholar
  2. 2.
    Daugman, J.: Demodulation by complex-valued wavelets for stochastic pattern recognition. Internat. J. Wavelets, Multi-Res. and Info. Processing 1, 1–17 (2003)zbMATHCrossRefGoogle Scholar
  3. 3.
    Deb, K.: Multi-Objective Optimization using Evolutionary Algorithms. J. Wiley Ltd., West Sussex (2004)Google Scholar
  4. 4.
    He, X., Shi, P.: An efficient iris segmentation method for recognition. In: Internat. Conf. on Adv. Pattern Recog. LNCS, vol. 3687, pp. 120–126. Springer, Heidelberg (2005)Google Scholar
  5. 5.
    Ma, L., Tan, T., Wang, Y., Zhang, D.: Efficient iris recognition by characterizing key local variations. IEEE Trans. Image Processing 13, 739–750 (2004)CrossRefGoogle Scholar
  6. 6.
    Son, B., Won, H., Kee, G., Lee, Y.: Discriminant iris feature and support vector machines for iris recognition. In: Internat. Conf. on Image Processing, vol. 2, pp. 865–868 (2004)Google Scholar
  7. 7.
    Sung, H., Lim, J., Park, J., Lee, Y.: Iris Recognition using collarette boundary localization. In: Proc. of Internat. Conf. on Pattern Recog., vol. 4 (2004)Google Scholar
  8. 8.
    Vapnik, V.N.: Statistical Learning Theory. J. Wiley Ltd., New York (1998)zbMATHGoogle Scholar
  9. 9.
  10. 10.
  11. 11.
    Iris Dataset obtained from West Virginia University (WVU),
  12. 12.
    Ding, P., Chen, Z., Liu, Y., Xu, B.: Asymmetrical support vector machines and application in speech processing. In: IEEE Internat. Conf. on Acousts, Speech, and Signal Process, vol. 1, pp. 73–76 (2002)Google Scholar
  13. 13.
    Oliveira, L.S., Sabourin, R.F., Bortolozzi, C.Y., Suen, C.Y.: Feature selection using multiobjective genetic algorithms for handwritten digit recognition. Internat. Conf. on Pattern Recog. 1, 568–571 (2002)Google Scholar
  14. 14.
    Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture models. IEEE Trans. On speech and audio process 3(1), 72–83 (1995)CrossRefGoogle Scholar
  15. 15.
    Tan, F., Fu, X., Zhang, Y., Bourgeois, A.G.: Improving feature subset selection using a genetic algorithm for microarray gene expression data. IEEE congress on evolutionary computation, 2529–2534 (2006)Google Scholar
  16. 16.
    Roy, K., Bhattacharya, P.: Iris Recognition Based on Collarette Region and Asymmetrical Support Vector Machines. In: Kamel, M., Campilho, A. (eds.) ICIAR 2007. LNCS, vol. 4633, pp. 854–865. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  17. 17.
    Roy, K., Bhattacharya, P.: Iris Recognition Using Support Vector Machine. In: IAPR Internat. Conf. on Biometric Authentication. LNCS, vol. 3882, pp. 486–492. Springer, Heidelberg (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Kaushik Roy
    • 1
  • Prabir Bhattacharya
    • 1
  1. 1.Concordia Institute For Information Systems Engineering (CIISE)Concordia UniversityMontrealCanada

Personalised recommendations