Advertisement

Object Recognition with Representations Based on Sparsified Gabor Wavelets Used as Local Line Detectors

  • Norbert Krüger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)

Abstract

We introduce an object recognition system (called ORAS-SYLL) in which objects are represented as a sparse and spatially organized set of local (bent) line segments. The line segments correspond to binarized Gabor wavelets or banana wavelets, which are bent and stretched Gabor wavelets. These features can be metrically organized, the metric enables an effcient learning of object representations. Learning can be performed autonomously by utilizing motor-controlled feedback. The learned representation are used for fast and effcient localization and discrimination of objects in complex scenes.

ORASSYLL has been heavily inuenced by an older and well known vision system 4, 9, and has also been inuenced by Biederman's comments to this older system [1]. A comparison of ORASSYLL and the older system, including some remarks about the specific role of Gabor wavelets within ORASSYLL, is given at the end of the paper.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    I. Biederman and P. Kalocsai. Neurocomputational bases of object and face recognition. Philosophical Transactions of the Royal Society: Biological Sciences, 352:1203–1219, 1997.CrossRefGoogle Scholar
  2. 2.
    N. Krüger. Collinearity and parallism are statistically significant second order relations of complex cell responses. Neural Processing Letters, 8(2), 1998.Google Scholar
  3. 3.
    N. Krüger. Visual Learning with a priori Constraints (Phd Thesis). Shaker Verlag, Germany, 1998.Google Scholar
  4. 4.
    M. Lades, J.C. Vorbrüuggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Würtz, and W. Konen. Distortion invariant object recognition in the dynamik link architecture. IEEE Transactions on Computers, 42(3):300–311, 1992.CrossRefGoogle Scholar
  5. 5.
    Y. Linde, A. Buzo, and R.M. Gray. An algorithm for vector quantizer design. IEEE Transactions on communication, vol. COM-28:84–95, 1980.CrossRefGoogle Scholar
  6. 6.
    H.S. Loos, B. Fritzke, and C. von der Malsburg. Positionsvorhersage von bewegten objekten in groformatigen bildsequenzen. Proceedings in Artificial Intelligence: Dynamische Perzeption, pages 31–38, 1998.Google Scholar
  7. 7.
    Michael Pötzsch, Thomas Maurer, Laurenz Wiskott, and Christoph von der Malsburg. Reconstruction from graphs labeled with responses of gabor filters. In C. v.d. Malsburg, W. v. Seelen, J.C. Vorbrüggen, and B. Sendhoff, editors, Proceedings of the ICANN 1996, Springer Verlag, Berlin, Heidelberg, New York, Bochum, July 1996.Google Scholar
  8. 8.
    J. Triesch and C. von der Malsburg. Robust classification of hand postures against complex background. Proceedings of the Second International Workshop on Automatic Face-and Gesture recognition, Vermont, pages 170–175, 1996.Google Scholar
  9. 9.
    L. Wiskott, J.M. Fellous, N. Krüger, and C. von der Malsburg. Face recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 775–780, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Norbert Krüger
    • 1
  1. 1.Institut für Informatik und praktischer MathematikChristian-Albrechts-Universität zu KielKielGermany

Personalised recommendations