Recognizing faces by weakly orthogonalizing against perturbations

  • Kenji Nagao
  • Masaki Sohma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)


In this paper, we address the problem of face recognition under drastic changes of the imaging processes through which the facial images are acquired. A new method is proposed. Unlike the conventional algorithms that use only the face features, the present method exploits the statistical information of the variations between the face image sets being compared, in addition to the features of the faces themselves. To incorporate the face and perturbation features for recognition, a technique called weak orthogonalization of the two subspaces has been developed that transforms the two overlapped subspaces such that the volume of the intersection of the resulting two subspaces is minimized. Matching is performed in the transformed face space that has thus been weakly orthogonalized against perturbation space. Results using real pictures of the frontal faces from drivers' licenses demonstrate the effectiveness of the new algorithm.


Face Recognition Face Image Face Space Face Recognition Task Correct Recognition Rate 
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.
    T. Kurita, N. Ohtsu and T. Sato, “A Face Recognition Method Using Higher Order Local Autocorrelation and Multivariate Analysis”, In Proc. IEEE ICPR92, pp. 213–216, 1992.Google Scholar
  2. 2.
    S. Akamatsu et. al., “An Accurate and Robust Face Identification Scheme”, In Proc. IEEE ICPR92, pp. 217–220, 1992.Google Scholar
  3. 3.
    M. Kirby, L. Sirovich, “Application of the Karhunen-Loeve procedure for the characterization of human faces”, IEEE Trans. Patt. Anal. Machine Intell., vol. 12, pp. 103–108, 1990.CrossRefGoogle Scholar
  4. 4.
    K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press 1972.Google Scholar
  5. 5.
    M. Turk, A. Pentland, “Face recognition using eigenfaces”, In Proc. IEEE CVPR91, 1991.Google Scholar
  6. 6.
    M. Turk, A. Pentland, “Eigenfaces for recognition”, Journal of Cognitive Neuroscience, vol. 3, No. 1, 1991.Google Scholar
  7. 7.
    A. Pentland, B. Moghaddam, T. Starner, “View-based and modular eigenspaces for face recognition”, In Proc. IEEE CVPR94, 1994.Google Scholar
  8. 8.
    R. Brunelli, T. Poggio, “Face Recognition: Features versus Template”, IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, pp.34–43, 1993.Google Scholar
  9. 9.
    N. Belhumeur, P. Hespanha, J. Kriegman, “Eigenfaces vs. fisherfaces:recognition using class specific linear projection”, In Proc. ECCV'96 voll pp. 45–58, 1996.Google Scholar
  10. 10.
    K. Fukunaga, W. C. G. Koontz, ”Application of the Karhunen-Loeve expansion to feature extraction and ordering”, IEEE Trans. Computers, Vol. C-19, pp. 311–318, 1970.Google Scholar
  11. 11.
    K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press 1972.Google Scholar
  12. 12.
    D. H. Foley, J. W. Sammon, ”An Optimal Set of Discriminant Vectors”, IEEE Trans. Computers, Vol. C-24, NO. 3, pp. 281–289, March 1975.Google Scholar
  13. 13.
    E. Oja, J. Karhunen, ”An Analysis of Convergence for a Learning Version of the Subspace Method”, J. Math. Anal. Applications 91. pp. 102–111, 1983.zbMATHMathSciNetCrossRefGoogle Scholar
  14. 14.
    E. Oja, Subspace Methods of Pattern Recognition, Research Studies Press LTD and John Wiley & Sons Inc., 1983.Google Scholar
  15. 15.
    J. Kittler, ”The subspace approach to pattern recognition”, in Progress in cybernetics and systems research, p. 92, Hamisphere Publ. Co., Washington, 1978.Google Scholar
  16. 16.
    T. Kohonen, P. Lehtio, E. Oja, ”Spectral classification of phonemes by learning subspacees”, Helsinki University of Technology, Dept. of Technical Physics, Report TKK-F-A348. Also in Proc. IEEE ICASP, pp. 2–4, April 1979.Google Scholar
  17. 17.
    S. Watanabe, N. Pakvasa, ”Subspace method of pattern recognition”, In Proc. IJCPR pp. 25–32, 1973.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Kenji Nagao
    • 1
  • Masaki Sohma
    • 1
  1. 1.Matsushita Research Institute TokyoKawasakiJapan

Personalised recommendations