Iris Recognition in Nonideal Situations

  • Kaushik Roy
  • Prabir Bhattacharya
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5735)


Most of the state-of-the-art iris recognition algorithms focus on processing and recognition of the ideal iris images which are captured in a controlled environment. In this paper, we process the nonideal iris images which are acquired in an unconstrained situation and are affected severely by gaze deviation, eyelids and eyelashes occlusion, non uniform intensity, motion blur, reflections, etc. To segment the nonideal iris images accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Genetic Algorithms (GAs) are deployed to select the subset of informative features by combining the valuable outcomes from the multiple feature selection criteria without compromising the recognition accuracy. The verification performance of the proposed scheme is validated using three nonideal iris datasets, namely, UBIRIS Version 2, ICE 2005, and WVU datasets.


Iris recognition variational level set method curve evolution genetic algorithms nonideal situations 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Daugman, J.: How iris recognition works. IEEE Transaction on Circuits, Systems and Video Technology 14(1), 1–17 (2003)zbMATHGoogle Scholar
  2. 2.
    Daugman, J.: New methods in iris recognition. IEEE Transactions on Systems, Man, and Cybernetics-Part B 37(5), 1167–1175 (2007)CrossRefGoogle Scholar
  3. 3.
    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 Transactions on Systems, Man, and Cybernetics-Part B 37(5), 1176–1190 (2007)CrossRefGoogle Scholar
  4. 4.
    Vatsa, M., Singh, R., Noore, A.: Improving iris recognition performance using segmentation, quality enhancement, match score fusion, and indexing. IEEE Transactions on Systems, Man, and Cybernetics-Part B 38(4), 1021–1035 (2008)CrossRefGoogle Scholar
  5. 5.
    Ross, A., Shah, S.: Segmenting non-ideal irises using geodesic active contours. In: Biometric Consortium Conference, IEEE Biometrics symposium, pp. 1–6 (2006)Google Scholar
  6. 6.
    Li, C., Xu, C., Gui, C., Fox, M.D.: Level set evolution without re-initialization: a new variational formulation. In: Int. Conf. on Comp. Vis. and Pattern Recog., vol. 1, pp. 430–436 (2005)Google Scholar
  7. 7.
    Deb, K.: Multi-objective Optimization using Evolutionary Algorithms. J. Wiley, West Sussex (2004)zbMATHGoogle Scholar
  8. 8.
    Roy, K., Bhattacharya, P.: Adaptive asymmetrical SVM and genetic algorithms based iris recognition. In: Int. Conf. on Pattern Recog., pp. 1–4 (2008)Google Scholar
  9. 9.
    Roy, K., Bhattacharya, P.: Level set approaches and adaptive asymmetrical SVMs applied for nonideal iris recognition. In: Kamel, M., Campilho, A. (eds.) ICIAR 2009. LNCS, vol. 5627, pp. 418–428. Springer, Heidelberg (2009)Google Scholar
  10. 10.
    Vapnik, V.N.: Statistical Learning Theory. J. Wiley, New York (1998)zbMATHGoogle Scholar
  11. 11.
    Li, Q., Jiao, L., Hao, Y.: Adaptive simplification of solution for support vector machine. Pattern Recognition 40, 972–980 (2007)CrossRefzbMATHGoogle Scholar
  12. 12.
    Iris Challenge Evaluation (ICE) dataset found,
  13. 13.
    Iris Dataset obtained from West Virginia University (WVU),
  14. 14.
    UBIRIS dataset obtained from department of computer science, University of Beira Interior, Portugal,

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Kaushik Roy
    • 1
  • Prabir Bhattacharya
    • 1
  1. 1.Concordia Institute for Information Systems EngineeringConcordia UniversityMontrealCanada

Personalised recommendations