While combining more than one biometric sample, recognition algorithm, modality or sensor, commonly referred to as multi-biometrics, is common practice to improve accuracy of biometric systems, fusion at segmentation level has so far been neglected in literature. This paper introduces the concept of multi-segmentation fusion for combining independent iris segmentation results. Fusion at segmentation level is useful to (1) obtain more robust recognition rates compared to single segmentation; (2) avoid additional storage requirements compared to feature-level fusion, and (3) save processing time compared to employing parallel chains of feature-extractor dependent segmentation. As proof of concept, manually labeled segmentation results are combined using the proposed technique and shown to increase recognition accuracy for representative algorithms on the well-known CASIA-V4-Interval dataset.


Discrete Cosine Transform Segmentation Result Manual Segmentation Fusion Rule Biometric System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bowyer, K.W., Hollingsworth, K.P., Flynn, P.J.: A survey of iris biometrics research: 2008-2010. In: Burge, M., Bowyer, K. (eds.) Handbook of Iris Recognition, pp. 15–54. Springer, New York (2012)Google Scholar
  2. 2.
    Daugman, J.: How iris recognition works. IEEE Trans. on Circiuts and Systems for Video Technology 14(1), 21–30 (2004)CrossRefGoogle Scholar
  3. 3.
    Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)CrossRefGoogle Scholar
  4. 4.
    Hollingsworth, K., Peters, T., Bowyer, K., Flynn, P.: Iris recognition using signal-level fusion of frames from video. IEEE Trans. Inf. Forensics and Sec. 4(4), 837–848 (2009)CrossRefGoogle Scholar
  5. 5.
    Jillela, R., Ross, A.: Mitigating effects of plastic surgery: Fusing face and ocular biometrics. In: Proc. 5th IEEE Int’l Conf. on Biometrics: Theory, App. and Syst., pp. 402–411 (2012)Google Scholar
  6. 6.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, Hoboken (2004)CrossRefGoogle Scholar
  7. 7.
    Ma, L., Tan, T., Wang, Y., Zhang, D.: Efficient iris recognition by characterizing key local variations. IEEE Transactions on Image Processing 13(6), 739–750 (2004)CrossRefGoogle Scholar
  8. 8.
    Masek, L., Kovesi, P.: MATLAB Source Code for a Biometric Identification System Based on Iris Patterns (2003),
  9. 9.
    Monro, D.M., Rakshit, S., Zhang, D.: Dct-based iris recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(4), 586–595 (2007)CrossRefGoogle Scholar
  10. 10.
    Proença, H., Alexandre, L.A.: Iris recognition: Analysis of the error rates regarding the accuracy of the segmentation stage. Image and Vision Comp. 28(1), 202–206 (2010)CrossRefGoogle Scholar
  11. 11.
    Proença, H., Alexandre, L.: Toward covert iris biometric recognition: Experimental results from the nice contests. IEEE Trans. Inf. Forensics and Sec. 7(2), 798–808 (2012)CrossRefGoogle Scholar
  12. 12.
    Rathgeb, C., Uhl, A., Wild, P.: Iris Recognition: From Segmentation to Template Security. Advances in Information Security, vol. 59. Springer, New York (2012)Google Scholar
  13. 13.
    Rathgeb, C., Uhl, A., Wild, P.: Incremental iris recognition: A single-algorithm serial fusion strategy to optimize time complexity. In: Proc. Int’l Conf. on Biometrics: Theory App. and Syst., pp. 1–6. IEEE (2010)Google Scholar
  14. 14.
    Ross, A., Jillela, R., Smereka, J., Boddeti, V., Kumar, B., Barnard, R., Hu, X., Pauca, P., Plemmons, R.: Matching highly non-ideal ocular images: An information fusion approach. In: Proc. 5th Int’l Conf. on Biometrics, pp. 446–453 (2012)Google Scholar
  15. 15.
    Ross, A.A., Nandakumar, K., Jain, A.K.: Handbook of Multibiometrics. Springer, Secaucus (2006)Google Scholar
  16. 16.
    Uhl, A., Wild, P.: Single-sensor multi-instance fingerprint and eigenfinger recognition using (weighted) score combination methods. Int’l Journal on Biometrics 1(4), 442–462 (2009)CrossRefGoogle Scholar
  17. 17.
    Uhl, A., Wild, P.: Enhancing iris matching using Levenshtein distance with alignment constraints. In: Bebis, G., et al. (eds.) ISVC 2010, Part I. LNCS, vol. 6453, pp. 469–478. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Vatsa, M., Singh, R., Noore, A., Ross, A.: On the dynamic selection of biometric fusion algorithms. IEEE Trans. on Inf. Forensics and Security 5(3), 470–479 (2010)CrossRefGoogle Scholar
  19. 19.
    Woodard, D., Pundlik, S., Miller, P., Jillela, R., Ross, A.: On the fusion of periocular and iris biometrics in non-ideal imagery. In: Proc. 20th Int’l Conf. on Pattern Recognition, pp. 201–204 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Andreas Uhl
    • 1
  • Peter Wild
    • 1
  1. 1.Multimedia Signal Processing and Security Lab. Department of Computer SciencesUniversity of SalzburgAustria

Personalised recommendations