Face recognition by elastic bunch graph matching

  • Laurenz Wiskott
  • Jean-Marc Fellous
  • Norbert Krüger
  • Christoph von der Malsburg
Face Analysis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)

Abstract

We present a system for recognizing human faces from single images out of a large database with one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise face descriptions in the form of image graphs. In these, fiducial points on the face (eyes, mouth etc.) are described by sets of wavelet components (jets). Image graph extraction is based on a novel approach, the bunch graph, which is constructed from a small set of sample image graphs. Recognition is based on a straight-forward comparison of image graphs. We report recognition experiments on the FERET database and the Bochum database, including recognition across pose.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    BUHMANN, J., LANGE, J., VON DER MALSBURG, C., VORBRüGGEN, J. C., AND Würtz R. P. Object recognition with Gabor functions in the dynamic link architecture: Parallel implementation on a transputer network. In Neural Networks for Signal Processing, B. Kosko, Ed. Prentice Hall, Englewood Cliffs, NJ 07632, 1992, pp. 121–159.Google Scholar
  2. [2]
    KRüGER, N. An algorithm for the learning of weights in discrimination functions using a priori constraints. accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997.Google Scholar
  3. [3]
    LADES, M., VORBRÜGGEN, J. C., BUHMANN, J., LANGE, J., VON DER MALSBURG, C., WüRTz, R. P., and KONEN, W. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers 42, 3 (1993), 300–311.CrossRefGoogle Scholar
  4. [4]
    MAURER, T., AND VON DER MALSBURG, C. Linear feature transformations to recognize faces rotated in depth. In Proceedings of the International Conference on Artificial Neural Networks, ICANN'95 (Paris, Oct. 1995), pp. 353–358.Google Scholar
  5. [5]
    PHILLIPS, P. J., RAUSS, P. J., AND DER, S. Z. FERET (face recognition technology) recognition algorithm development and test report. Tech. Rep. ARL-TR-995, U. S. Army Research Laboratory, 2800 Powder Mill Road, Adelphi, MD 20783-1197, Oct. 1996.Google Scholar
  6. [6]
    RAUSS, P. J., PHILLIPS, J., HAMILTON, M. K., AND DEPERSIA, A. T. FERET (face-recognition technology) recognition algorithms. In Proc. of the Fifth Automatic Target Recognizer System and Technology Symposium. (1996).Google Scholar
  7. [7]
    WISKOTT, L. Phantom faces for face analysis. Pattern Recognition 30, 6 (1996).Google Scholar
  8. [8]
    WISKOTT, L., FELLOUS, J.-M., KRÜGER, N., AND VON DER MALSBURG, C. Face recognition by elastic bunch graph matching. Tech. Rep. IR-INI 96-08, Institut für Neuroinformatik, Ruhr-Universitiit Bochum, D-44780 Bochum, Germany, 1996.Google Scholar

Copyright information

© Springer-Verlag 1997

Authors and Affiliations

  • Laurenz Wiskott
    • 1
  • Jean-Marc Fellous
    • 2
  • Norbert Krüger
    • 1
  • Christoph von der Malsburg
    • 1
    • 2
  1. 1.Institut für NeuroinformatikRuhr-Universität BochumBochumGermany
  2. 2.Computer Science DepartmentUniversity of Southern CaliforniaLos AngelesUSA
  3. 3.Computational Neurobiology LaboratoryThe Salk Institute for Biological StudiesSan Diego
  4. 4.Volen Center for Complex SystemsBrandeis UniversityWaltham

Personalised recommendations