A Novel Model for Gabor-Based Independent Radial Basis Function Neural Networks and Its Application to Face Recognition

  • GaoYun An
  • QiuQi Ruan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


In this paper, a novel model for Gabor-based independent radial basis function (IRBF) neural network is proposed and applied to face recognition. In the new model, a bank of Gabor filters is first built to extract Gabor face representations characterized by selected frequency, locality and orientation to cope with various illuminations, facial expression and poses in face recognition. Then principal component analysis (PCA) is adopted to reduce the dimension of the extracted Gabor face representations for every face sample. At last, a new IRBF neural network is built to extract high-order statistical features of extracted Gabor face representations with lower dimension and to classify these extracted high-order statistical features. According to the experiments on the famous CAS-PEAL face database, our proposed approach could outperform ICA with architecture II (ICA2) and kernel PCA (KPCA) with standing testing sets proposed in the current release disk of the CAS-PEAL face database.


Face Recognition Radial Basis Function Neural Network Gabor Filter Face Database Kernel Principal Component Analysis 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Liu, C.J.: Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Trans. PAMI 26, 572–581 (2004)Google Scholar
  2. 2.
    Meng, J.E., Wu, S., Lu, J., Hock, L.T.: Face recognition with radial basis function (RBF) neural networks. IEEE Trans. Neural Networks 13, 697–710 (2002)CrossRefGoogle Scholar
  3. 3.
    Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10, 1299–1319 (1998)CrossRefGoogle Scholar
  4. 4.
    Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: Face recognition by independent component analysis. IEEE Trans. Neural Networks 13, 1450–1464 (2002)CrossRefGoogle Scholar
  5. 5.
    Yang, J., Gao, X., Zhang, D., Yang, J.: Kernel ICA: An alternative formulation and its application to face recognition. Pattern Recognition 38, 1784–1787 (2005)MATHCrossRefGoogle Scholar
  6. 6.
    Turk, M., Pentland, A.: Eigenfaces for Recognition. Cognitive Neuroscience 3, 71–86 (1991)CrossRefGoogle Scholar
  7. 7.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans. PAMI 19, 711–720 (1997)Google Scholar
  8. 8.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Pearson Education, USA (1999)MATHGoogle Scholar
  9. 9.
    Gao, W., Cao, B., Shan, S., Zhou, D., Zhang, X., Zhao, D.: The CAS-PEAL large-scale Chinese face database and evaluation protocols. Technical Report No. JDL_TR_04_FR_001, Joint Research & Development Laboratory, CAS (2004)Google Scholar
  10. 10.
    Delac, K., Grgic, M., Grgic, S.: Independent Comparative Study of PCA, ICA, and LDA on the FERET Data Set. Technical Report, University of Zagreb, FER (2004),
  11. 11.
    Bell, A.J., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Computing 7, 1129–1159 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • GaoYun An
    • 1
  • QiuQi Ruan
    • 1
  1. 1.Institute of Information ScienceBeijing Jiaotong UniversityBeijingChina

Personalised recommendations