A Transformation-Based Mechanism for Face Recognition

  • Yea-Shuan Huang
  • Yao-Hong Tsai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)


This paper proposes a novel mechanism to seamlessly integrate face detection and face recognition. After extracting a human face x from an input image, not only x but also its various kinds of transformations are performed recognition. The final decision is then derived from aggregating the accumulated recognition results of each transformed pattern. From experiments, the proposed method has shown a significantly improved recognition performance compared with the traditional method on recognizing human faces.


Face Recognition Face Image Face Detection Face Database Face Recognition 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.
    K.K. sung and T. Poggio, “Example-Based Learning for view-Based Human Face Detection,” IEEE Trans. Patt. Anal. Machine Intell., Vol. 20, pp. 39–51, 1998.CrossRefGoogle Scholar
  2. 2.
    H. A. Rowley, S. Baluja, and T. Kanade, “Neural network-based face detection,” IEEE transactions on PAMI., vol. 20, no. 1, pp. 22–38, Jan. 1998.Google Scholar
  3. 3.
    D. M. Gavrila, “The visual analysis of human movement: a survey,” Computer Vision and Image Understanding, vol. 73, pp. 82–98, 1999.zbMATHCrossRefGoogle Scholar
  4. 4.
    M. Turk and A. Pentland, “Eihenfaces for Recognition”, Journal of Cognitive Neuroscience, March, 1991.Google Scholar
  5. 5.
    R. Brunelli and T. Poggio, “Face Recognition: Features Versus Templates”, IEEE Trans. Patt. Anal. Machine Intell. Vol. 15, No. 10, October, pp 1042–1052, 1993.CrossRefGoogle Scholar
  6. 6.
    R. Chellappa, C. Wilson and S. Sirohey, “Human and Machine Recognition of Faces: A Survey”, Proc. Of IEEE, Vol. 83, No. 5, May, pp 705–740, 1995.CrossRefGoogle Scholar
  7. 7.
    A.K. Jain, R. Bolle and S. Pankanti, Biometrics: Personal Identification in Networked Society, Kluwer Academic Publishers, 1999.Google Scholar
  8. 8.
    L.-F. Chen, C.-C. Han, and J.-C. Lin, “Why Recognition in a Statistics-Based Face Recognition System Should be Based on the Pure Face Portion: a Probabilistic Decision-Based Proof,” to appear in Pattern Recognition, 2001.Google Scholar
  9. 9.
    F. Goudail, E. Lange, T. Iwamoto, K. Kyuma, and N. Otsu, “Face Recognition System Using Local Autocorrelations and Multiscale Integrations,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 18, pp. 1024–1028, Oct., 1996.Google Scholar
  10. 10.
    C.C. Han, H.Y. Mark, K.C. Yu, and L.H. Chen, “Fast Face Detection via Morphology-Based Pre-Processing,” Pattern Recognition 33, pp. 1701–1712, 2000.CrossRefGoogle Scholar
  11. 11.
    B.H. Juang and S. Katagiri, “Discriminative Learning for Minimum Error Classification”, IEEE Trans. On Signal Processing, Vol. 40, No. 12, December, pp3043–3054, 1992.zbMATHCrossRefGoogle Scholar
  12. 12.
    Yea-Shuan Huang, Yao-Hong Tsai, Jun-Wei Shieh, “Robust Face Recognition with Light Compensation,” to appear in The Second IEEE Pacific-Rim Conference on Multimedia, 2001.wGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Yea-Shuan Huang
    • 1
  • Yao-Hong Tsai
    • 1
  1. 1.Advanced Technology Center Computer & Communications Research LaboratoriesIndustrial Technology Research InstituteChutung, HsinchuTaiwan

Personalised recommendations