A Random Network Ensemble for Face Recognition

  • Kwontaeg Choi
  • Kar-Ann Toh
  • Hyeran Byun
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5558)


In this paper, we propose a random network ensemble for face recognition problem, particularly for images with a large appearance variation and with a limited number of training set. In order to reduce the correlation within the network ensemble using a single type of feature extractor and classifier, localized random facial features have been constructed together with internally randomized networks. The ensemble classifier is finally constructed by combining these multiple networks via a sum rule. The proposed method is shown to have a better accuracy(31.5% and 15.3% improvements on AR and EYALEB databases respectively) and a better efficiency than that of the widely used PCA-SVM.


Face recognition random projection neural network 


  1. 1.
    Raudys, S.J., Jain, A.K.: Small Sample Size Effects in Statistical Pattern Recognition Recommendations for Practitioners. IEEE Trans on Pattern Analysis and Machine Intelligence 13(3), 252–264 (1991)Google Scholar
  2. 2.
    Skurichina, M., Duin, R.: Bagging, boosting and the random subspace method for linear classifiers. Pattern Anal. Appl., 121–135 (2002)Google Scholar
  3. 3.
    Lu, X., Wang, Y., Jain, A.K.: Combining classifiers for face recognition. In: ICME (2003)Google Scholar
  4. 4.
    Lu, X., Jain, A.K.: Resampling for Face Recognition. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688. Springer, Heidelberg (2003)Google Scholar
  5. 5.
    Wang, X., Tang, X.: Random sampling face recognition. International Journal of Computer Vision (IJCV) (2005)Google Scholar
  6. 6.
    Zhang, X., Jia, Y.: A linear discriminant analysis framework based on random subspace for face recognition. In: Proceedings of Pattern Recognition, pp. 2585–2591 (2007)Google Scholar
  7. 7.
    Lemieux, A., Parizeau, M.: Flexible multi-classifier architecture for face recognition systems. In: The 16th International Conference on Vision Interface (2003)Google Scholar
  8. 8.
    Goel, N., Bebis, G., Nefian, A.: Face recognition experiments with random projection. In: SPIE (2005)Google Scholar
  9. 9.
    Achlioptas, D.: Database-friendly random projections. In: ACM Symposium on the Principles of Database Systems, pp. 274–281 (2001)Google Scholar
  10. 10.
    Li, P., Hastie, T., Church, K.W.: Very sparse random projections. In: KDD, pp. 287–296 (2006)Google Scholar
  11. 11.
    Feng, Li, S.Z., Shum, H.Y., Zhang, H.J.: Local non-negative matrix factorization as a visual representation. In: The Second International Conference on Development and Learning, pp. 178–183 (2002)Google Scholar
  12. 12.
    Er, M.J., Wu, S., Lu, J., Toh, H.L.: Face recognition with radial basis function (RBF) neural networks. IEEE Trans. Neural Netw. 13, 697–710Google Scholar
  13. 13.
    Huang, G.-B., Siew, C.-K.: Extreme learning machine with randomly assigned RBF kernels. International Journal of Information Technology 11(1) (2005)Google Scholar
  14. 14.
    Liang, N.Y., Huang, G.B., Saratchandran, P., Sundararajan, N.: A Fast and Accurate On-Line Sequential Learning Algorithm for Feedforward Networks. IEEE Trans. Neural Networks 17, 1411–1423 (2006)Google Scholar
  15. 15.
  16. 16.
    Martinez, A., Benavente, R.: The AR Face Database (1998)Google Scholar
  17. 17.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Trans. Pattern Anal. Mach. Intelligence 23(6), 643–660 (2001)Google Scholar
  18. 18.
    Sim, T., Baker, S., Bsat, M.: The CMU Pose, Illumination, and Expression Database. IEEE Trans. Pattern Anal. Mach. Intelligence 25(12), 1615–1618 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Kwontaeg Choi
    • 1
  • Kar-Ann Toh
    • 2
  • Hyeran Byun
    • 1
  1. 1.Dept. of Computer ScienceYonsei UniversitySeoulSouth Korea
  2. 2.School of Electrical & Electronic EngineeringYonsei UniversitySeoulSouth Korea

Personalised recommendations