Face Detection by Learned Affine Correspondences

  • Miroslav Hamouz
  • Josef Kittler
  • Jiri Matas
  • Petr Bílek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)


We propose a novel framework for detecting human faces based on correspondences between triplets of detected local features and their counterparts in an affine invariant face appearance model. The method is robust to partial occlusion, feature detector failure and copes well with cluttered background. Both the appearance and configuration probabilities are learned from examples. The method was tested on the XM2VTS database and a limited number of images with cluttered background with promising results — 2% false negative rate — was obtained.


Face Feature False Negative Rate Feature Detector Face Detection Appearance Model 
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. [BLP95]
    M. C. Burl, T. K. Leung, and P. Perona. Face localization via shape statistics. In Proc. of International Workshop on Automatic Face and Gesture Recognition, pages 154–159, 1995.Google Scholar
  2. [BP96]
    M. C. Burl and P. Perona. Recognition of planar object classes. In Proc. of Computer Vision and Pattern Recognition, pages 223–230, 1996.Google Scholar
  3. [BWP98]
    M. C. Burl, M. Weber, and P. Perona. A Probabilistic approach to object recognition using local photometry abd global Geometry. In Proc. of European Conference on Computer Vision, pages 628–641, 1998.Google Scholar
  4. [BY98]
    V. Bruce and A. Young. In the Eye of Beholder, The Science of face perception. Oxford University Press, 1998.Google Scholar
  5. [KP97]
    C. Kotropoulos and I. Pitas. Rule-based face detection in frontal views. In Proc. of International Conference on Acoustics, Speech, and Signal Processing, pages 21–24, 1997.Google Scholar
  6. [LVB+93]
    M. Lades, J. C. Vorbrüggen, J. Buhmann, J. Lange, Ch. von der Malsburg, R. P. Würtz, and W. Konen. Distrotion invariant object recognition in the dynamic link architecture. IEEE Trans. on Pattern Analysis and Machine Intelligence, 42(3):300–310, 1993.Google Scholar
  7. [MBHK02]
    J. Matas, P. Bílek, M. Hamouz, and J. Kittler. Discriminative regions for human face detection. In Proceedings of Asian Conference on Computer Vision, January 2002.Google Scholar
  8. [MMK+99]
    K. Messer, J. Matas, J. Kittler, J. Luettin, and G. Maitre. XM2VTSDB: The extended M2VTS database. In R. Chellapa, editor, Second International Conference on Audio and Video-based Biometric Person Authentication, pages 72–77, Washington, USA, March 1999. University of Maryland.Google Scholar
  9. [MP95]
    B. Moghaddam and A. Pentland. Probabilistic visual learning for object detection. In Proc. of International Conference on Computer Vision, pages 786–793, 1995.Google Scholar
  10. [MP96]
    B. Moghaddam and A. Pentland. Probabilistic visual learning for object representation. In Early Visual Learning, pages 99–130. Oxford University Press, 1996.Google Scholar
  11. [SK98]
    H. Schneiderman and T. Kanade. Probabilistic modeling of local appearance and spatial relationships for object recognition. In Proc. Computer Vision and Pattern Recognition, pages 45–51. IEEE, 1998.Google Scholar
  12. [SP98]
    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.Google Scholar
  13. [VS00]
    V. Vogelhuber and C. Schmid. Face detection based on generic local descriptors and spatial constraints. In Proc. of International Conference on Computer Vision, pages I:1084–1087, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Miroslav Hamouz
    • 1
  • Josef Kittler
    • 1
  • Jiri Matas
    • 1
  • Petr Bílek
    • 1
  1. 1.Centre for Vision, Speech and Signal ProcessingUniversity of SurreyUK

Personalised recommendations