Hypotheses-Driven Affine Invariant Localization of Faces in Verification Systems

  • M. Hamouz
  • J. Kittler
  • J. K. Kamarainen
  • H. Kälviäinen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


We propose a novel framework for localizing human faces in client authentication scenarios based on correspondences between triplets of detected Gabor-based local features and their counterparts in a generic affine invariant face appearance model. The method is robust to partial occlusion, feature detector failure and copes well with cluttered background. The method was tested on the BANCA database and produced promising results.


Face Detection Appearance Model Invariant Localization Gabor Feature Face Space 
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. [2]
    G. J. Edwards, C. J. Taylor, and T. F. Cootes. Learning to identify and track faces in image sequences. In ICCV, 317–322, 1998.Google Scholar
  2. [3]
    S. Gong, A. Psarrou, and S. Romdhani. Corresponding dynamic appearences. Image and Vision Computing, 20:307–318, 1997.CrossRefGoogle Scholar
  3. [4]
    M. Hamouz, J. Kittler, J. Matas, and P. Bílek. Face detection by learned affine correspondences. In Proceedings of Joint IAPR International Workshops SSPR02 and SPR02, 566–575, August 2002.Google Scholar
  4. [5]
    O. Jesorsky, K. J. Kirchberg, and R.W. Frischholz. Robust Face Detection Using the Hausdorff Distance. In AVBPA 2001, 90–95, volume 2091 of J. Bigun and F. Smeraldi, Lecture Notes in Computer Science, Halmstad, Sweden, 2001. Springer.Google Scholar
  5. [6]
    J.-K. Kamarainen, V. Kyrki, and H. Kälviäinen. Fundamental frequency Gabor filters for object recognition. In 16th International Conference on Pattern Recognition ICPR, 1:628–631, Quebec, Canada, 2002.Google Scholar
  6. [7]
    J.-K. Kamarainen, V. Kyrki, H. Kälviäinen, M. Hamouz, and J. Kittler. Invariant Gabor features for evidence extraction. In Proceedings of MVA2002 IAPR Workshop on Machine Vision Applications, 228–231, 2002.Google Scholar
  7. [8]
    A. Kostin, M. Sadeghi, J. Kittler, and K. Messer. On representation spaces for SVM based face verification. In M. Falcone, A. Ariyaeeinia, and A. Paoloni, The advent of biometrics on the internet, 9–16, 2002.Google Scholar
  8. [9]
    J. Lampinen, T. Tamminen, T. Kostiainen, and I. Kallioäki. Bayesian object matching based on mcmc sampling and gabor filters. In Proc. SPIE Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, 41–50, volume 4572, 2001.Google Scholar
  9. [10]
    M. Lades, J. C. Vorbrüggen, J. Buhmann, J. Lange, C. v.d. Malsburg, R.P. Würtz, and W. Konen. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42(3):300–311, Mar 1993.CrossRefGoogle Scholar
  10. [11]
    S. J. McKenna and S. Gong. Real-time pose estimation. Journal of Real-Time Imaging, 4:333–347, 1998.CrossRefGoogle Scholar
  11. [12]
    Hyun Jin Park and Seung Yang. Invariant object detection based on evidence accumulation and Gabor features. Pattern Recognition Letters, 22:869–882, 2001.zbMATHCrossRefGoogle Scholar
  12. [13]
    S. Romdhani, S. Gong, and A. Psarrou. A generic face appearance model of shape and texture under very large pose variations from profile to profile views. In Proc. of ICPR, 1:1060–1064, 2000.Google Scholar
  13. [14]
    K. Sung and T. Poggio. Example-based learning for view-based human face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(1):39–50, January 1998.CrossRefGoogle Scholar
  14. [15]
    F. Torre, S. Gong, and S. McKenna. View-based adaptive affine tracking. In Proc. of ECCV, 1:828–842, 1998.Google Scholar
  15. [16]
    P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, 1:511–518, 2001.Google Scholar
  16. [17]
    V. Vogelhuber and C. Schmid. Face detection based on generic local descriptors and spatial constraints. In Proc. of International Conference on Computer Vision, 1084–1087, 2000.Google Scholar
  17. [18]
    M. Weber, M. Welling, and P. Perona. Unsupervised learning of models for recognition. In Proc. 6th Europ. Conf. Comput. Vision, Dublin, Ireland, 1:18–32, 2000.Google Scholar
  18. [19]
    K. Yow and R. Cipolla. Towards an automatic human face localization system. In Proc. of BMVC, 2:307–318, 1995.Google Scholar
  19. [20]
    K. Yow and R. Cipolla. Feature-based human face detection. Image and Vision Computing, 15:713–735, 1997.CrossRefGoogle Scholar
  20. [21]
    S.Y. Li, S. Gong, and H. Liddell. Modelling faces dynamically across views and over time. In Proc. of ICCV, 554–559, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • M. Hamouz
    • 1
  • J. Kittler
    • 1
  • J. K. Kamarainen
    • 2
  • H. Kälviäinen
    • 2
  1. 1.Centre for Vision, Speech and Signal ProcessingUniversity of SurreyUK
  2. 2.Laboratory for Information ProcessingLappeenranta University of TechnologyFinnland

Personalised recommendations