Multibiometric System Using Level Set Method and Particle Swarm Optimization

  • Kaushik Roy
  • Mohamed S. Kamel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7325)


Multibiometric systems alleviate some of the drawbacks possessed by the single modal biometric trait and provide better recognition accuracy. This paper presents a multimodal system that integrates the iris, face, and gait features based on the fusion at feature level. The novelty of this research effort is that a feature subset selection scheme based on Particle Swarm Optimization (PSO) is proposed to select the optimal subset of features from the fused feature vector. In addition, we apply a Variational Level Set (VLS)-based curve evolution scheme to detect the silhouette shape structure. Experimental results indicate that the proposed approach increases biometric recognition accuracies compared to that produced by single modal biometrics.


Multibiometrics variational level set active shape model particle swarm optimization feature subset selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Liau, H., Isa, D.: Feature selection for support vector machine-based face-iris multimodal biometric system. Expert Syst. with Appl. 38(9), 11105–11111 (2011)CrossRefGoogle Scholar
  2. 2.
    Ross, A., Govindarajan, R.: Feature level fusion using hand and face biometrics. In: Proc. SPIE Intl. Conf. on Biometric Tech. for Human Identification II, vol. 5779, pp. 196–204 (2005)Google Scholar
  3. 3.
    Rattani, A., Tistarelli, M.: Robust Multi-modal and Multi-unit Feature Level Fusion of Face and Iris Biometrics. In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 960–969. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Rattani, A., Kisku, D., Bicego, M., Tistarelli, M.: Feature level fusion of face and fingerprint biometrics. In: Proc. Intl. IEEE Conf. on Biometrics: Theory, Appl., and Syst., pp. 1–5 (2009)Google Scholar
  5. 5.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proc. IEEE Intl. Conf. on Neural Networks, vol. 4, pp. 1942–1948 (1995)Google Scholar
  6. 6.
    Raghavendra, R., Dorizzi, B., Rao, A., Hemantha, G.: PSO versus AdaBoost for feature selection in multimodal biometrics. In: Proc. IEEE Intl. Conf. on Biometrics: Theory, Appl., and Syst., pp. 1–7 (2009)Google Scholar
  7. 7.
    Roy, K., Bhattacharya, P., Suen, C.: Iris segmentation using variational level set method. Optics and Lasers in Engg. 49(4), 578–588 (2011)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Li, C., Xu, C., Gui, C., Fox, M.: Level set evolution without re-initialization: a new variational formulation. In: Proc. IEEE Intl. Conf. Comp. Vis. and Pattern Recog., vol. 1, pp. 430–436 (2005)Google Scholar
  9. 9.
    Ginneken, B., Frangi, A., Staal, J., Romeny, B., Viergever, M.: Active shape model segmentation with optimal features. IEEE Trans. Medical Imaging 21(8), 924–933 (2002)CrossRefGoogle Scholar
  10. 10.
    Wang, L., Tan, T., Ning, H., Hu, W.: Silhouette analysis-based gait recognition for human identification. IEEE Trans. Pattern Anal. and Machine Intell. 25(12), 1505–1518 (2003)CrossRefGoogle Scholar
  11. 11.
    Vapnik, V.: Statistical Learning Theory. John Wiley & Sons, New York (1998)zbMATHGoogle Scholar
  12. 12.
    CASIA-Iris Version 3 dataset found at,
  13. 13.
  14. 14.
  15. 15.
    Goldberg, G.: Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Professional (1989)Google Scholar
  16. 16.
    Makrehchi, M., Kamel, M.: Aggressive feature selection by feature ranking. In: Liu, H., Motoda, H. (eds.) Computational Methods of Feature Selection, pp. 313–330. Chapman and Hall/CRC Press (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Kaushik Roy
    • 1
  • Mohamed S. Kamel
    • 1
  1. 1.Centre for Pattern Analysis and Machine IntelligenceUniversity of WaterlooCanada

Personalised recommendations