Boosting a Haar-Like Feature Set for Face Verification

  • Bernhard Fröba
  • Sandra Stecher
  • Christian Küblbeck
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


This paper describe our ongoing work in the field of face verification. We propose a novel verification method based on a set of haar-like features which is optimized using AdaBoost. Seven different types of generic kernels constitute the starting base for the feature extraction process. The convolution of the di.erent kernels with the face image, each varying in size and aspect-ratio, leeds to a high-dimensional feature space (270000 for an image of size 64x64). As the number of features quadruples the number of pixels in the original image we try to determine only the most discriminating features for the verification task. The selection of a few hundred of the most discriminative features is performed using the Ada-Boost training algorithm. Experimental results are presented on the M2VTS-database according to the Lausanne-Protocol, where we can show that a reliable verification system can be realized representing a face with only 200 features.


Face Recognition Face Image Kernel Size Kernel Type Kernel Width 
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]
    Y. Freund and R. Schapire. A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14(5), pages 771–780, September 1999.Google Scholar
  2. [2]
    Guodong Guo and Hong-Jiang Zhang. Boosting for fast face recognition. Technical report, Microsoft Research, Februar 2001.Google Scholar
  3. [3]
    J. Luettin and G. Maître. Evaluation protocol for the extended M2VTS database (XM2VTSDB). IDIAP-COM 05, IDIAP, 1998.Google Scholar
  4. [4]
    J. Matas, M. Hamouz, K. Jonsson, J. Kittler, Y. Li, C. Kotropoulos, A. Tefas, I. Patas, T. Tan, H Yan, F Smeraldi, J. Bigun, N. Capdevielle, W. Gerstner, S. Ben-Yacoub, Y. Abdeljaoued, and E. Mayoraz. Comparison of face verification results on the XM2VTS database. In Proc. Int. Conf. on Patt. Rec. ICPR-15. IEEE Computer Society, 2000.Google Scholar
  5. [5]
    K. Messer, J. Matas, J. Kittler, J. Luettin, and G. Maître. Xm2vtsdb: The extended m2vts database. In Second International Conference on Audio-and Videobased Biometric Person Authentication, pages 71–77, 1999.Google Scholar
  6. [6]
    M.A. Turk and A.P. Pentland. Face recognition using eigenfaces. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 586–591, June 1991.Google Scholar
  7. [7]
    Paul Viola and Michael Jones. Robust real-time object detection, 2001.Google Scholar
  8. [8]
    Laurenz Wiskott. Phantom faces for analysis. Pattern Recognition, 30(6):837–846, 1997.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Bernhard Fröba
    • 1
  • Sandra Stecher
    • 1
  • Christian Küblbeck
    • 1
  1. 1.Fraunhofer-Institute for Integrated CircuitsErlangenGermany

Personalised recommendations