Advertisement

Affine / photometric invariants for planar intensity patterns

  • Luc Van Gool
  • Theo Moons
  • Dorin Ungureanu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)

Abstract

The paper contributes to the viewpoint invariant recognition of planar patterns, especially labels and signs under affine deformations. By their nature, the information of such ‘eye-catchers’ is not contained in the outline or frame — they often are affinely equivalent like parallelograms and ellipses — but in the intensity content within. Moment invariants are well suited for their recognition. They need a closed bounding contour, but this is comparatively easy to provide for the simple shapes considered. On the other hand, they characterize the intensity patterns without the need for error prone feature extraction. This paper uses moments as the basic features, but extends the literature in two respects: (1) deliberate mixes of different types of moments to keep the order of the moments (and hence also the sensitivity to noise) low and yet have a sufficiently large number to safeguard discriminant power; and (2) invariance with respect to photometric changes is incorporated in order to find the simplest moment invariants that can cope with changing lighting conditions which can hardly be avoided when changing viewpoint. The paper gives complete classifications of such affine / photometric moment invariants. Experiments are described that illustrate the use of some of them.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. Abo-Zaid, O. Hinton, and E. Horne, About moment normalisation and complex moment descriptors, Proc. 4th International Conference on Pattern Recognition, pp.399–407, 1988.Google Scholar
  2. 2.
    J. Flusser and T. Suk, Pattern recognition by affine moment invariants, Pattern Recognition, Vol. 26, No. 1, pp.167–174, 1993.Google Scholar
  3. 3.
    M. Hu, Visual pattern recognition by moment invariants, IRE Trans. Information Theory, IT-8, pp.179–187, 1962.Google Scholar
  4. 4.
    S. Maitra, Moment invariants, Proc. IEEE, Vol.67, pp.697–699, 1979.Google Scholar
  5. 5.
    J.L. Mundy and A. Zisserman (eds.), Geometric Invariance in Computer Vision, MIT Press, Cambridge, Massachusetts, 1992.Google Scholar
  6. 6.
    J.L. Mundy, A. Zisserman, and D. Forsyth (eds.), Applications of Invariance in Computer Vision, Lecture Notes in Computer Science, Vol. 825, pp. 89–106, Springer-Verlag, Berlin / Heidelberg / New York / Tokyo, 1994.Google Scholar
  7. 7.
    M. Oren and S. Nayar, Seeing beyond Lambert's law, Proc. European Conference on Computer Vision, pp. 269–280, 1994.Google Scholar
  8. 8.
    R. Prokop and A. Reeves, A survey of moment-based techniques for unoccluded object representation and recognition, CVGIP: Models and Image Processing, Vol.54, No.5, pp. 438–460, 1992.Google Scholar
  9. 9.
    T. Reiss, Recognizing planar objects using invariant image features, Lecture Notes in Computer Science, Vol. 676, pp. 89–106, Springer-Verlag, Berlin / Heidelberg / New York / Tokyo, 1993.Google Scholar
  10. 10.
    H. Schulz-Mirbach, Anwendung von Invarianzprinzipien zur Merkmalgewinnung in der Mustererkennung, VDI Verlag, 1995.Google Scholar
  11. 11.
    C.-H. Teh and R. Chin, On image analysis by the methods of moments, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, No. 4, pp. 496–513, 1988.Google Scholar
  12. 12.
    L. Van Gool, T. Moons, E. Pauwels and A. Oosterlinck, Vision and Lie's approach to invariance, Image and Vision Computing, Vol. 13 (1995), no. 4, pp. 259–277.Google Scholar
  13. 13.
    L. Van Gool, T. Moons, and D. Ungureanu, Affine /photometric invariants for planar intensity patterns, K.U.Leuven Technical Report KUL/ESAT/MI2/9511, Katholieke Universiteit Leuven, Belgium, 1995.Google Scholar
  14. 14.
    L. Wolff, On the relative brightness of specular and diffuse reflection, Proc. Computer Vision and Pattern Recognition, pp.369–376, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Luc Van Gool
    • 1
  • Theo Moons
    • 1
  • Dorin Ungureanu
    • 1
  1. 1.ESAT - MI2Katholieke Universiteit LeuvenHeverleeBelgium

Personalised recommendations