Efficient matching with invariant local descriptors

  • Roger Mohr
  • Patrick Gros
  • Cordelia Schmid
Invited Talks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


We are addressing the problem of matching images of scene or of objects when a large collection of reference objects is considered. The paper addresses also the issue of dealing with illumination change and camera position changes. Our approach is firstly based on the use of invariants. Invariants have to be computed locally so that the resulting values will not affected by partial occlusion or accidental highlights. In- variants proved to be a very discriminant piece of information and stored in a hash table they allow efficient indexing of visual shape. Final recognition can be performed using simply a robust voting technique or can be improved using Bayesian decision.


Interest Point Query Image Illumination Change Partial Visibility Aerial Image 
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. 1.
    N. Ayache and O.D. Faugeras. HYPER: a new approach for the recognition and positioning of 2D objects. PAMI, 8(1):44–54, 1986.Google Scholar
  2. 2.
    K. Barnard, G. Finlayson, and B. Funt. Colour constancy for scenes with varying illumination. In ECCV, pages 3–15, July 1996.Google Scholar
  3. 3.
    S. Berchtold, D.A. Keim, and H.P. Kriegel. The X-tree: An index structure for high-dimensional data. In Proceedings of the 22nd VLDB Conference, Mumbai (Bombay), India, pages 28–39. the Very Large Database Endowment, 1996.Google Scholar
  4. 4.
    P.J. Besl and R.C. Jain. Three-dimensional object recognition. Acm Computing Surveys, 17(1), 1985.Google Scholar
  5. 5.
    T.O. Binford and T.S. Levitt. Quasi-invariants: Theory and exploitation. In Proceedings of darpa Image Understanding Workshop, pages 819–829, 1993.Google Scholar
  6. 6.
    R.C. Bolles and R. Horaud. 3DPO: A three-dimensional Part Orientation system. IJRR, 5(3):3–26, 1986.Google Scholar
  7. 7.
    A. Califano and R. Mohan. Multidimensional indexing for recognizing visual shapes. PAMI, 16(4):373–392, April 1994.Google Scholar
  8. 8.
    J.L. Chen and G.C. Stockman. Matching curved 3D object models to 2D images. In A.C. Kak and K. Ikeuchi, editors, Proceedings of the Second CAD-Based Vision Workshop, pages 210–218, Los Alamitos, California, February 1994. IEEE Computer Society Press.Google Scholar
  9. 9.
    R.T. Chin, H. Smith, and S.C. Fralik. Three-dimensional object recognition. ACM Computing Surveys, 17(1):75–145, 1986.Google Scholar
  10. 10.
    L.M.T. Florack, B. ter Haar Romeny, J.J Koenderink, and M.A. Viergever. General intensity transformation and differential invariants. Journal of Mathematical Imaging and Vision, 4(2):171–187, 1994.CrossRefGoogle Scholar
  11. 11.
    G. Florou and R. Mohr. What accuracy for 3D measurements with cameras? In ICPR, volume I, pages 354–358, 1996.Google Scholar
  12. 12.
    B.V. Funt and G.D. Finlayson. Color constant color indexing. PAMI, 17(5):522–529, 1995.Google Scholar
  13. 13.
    C. Harris and M. Stephens. A combined corner and edge detector. In Alvey Vision Conference, pages 147–151, 1988.Google Scholar
  14. 14.
    J.J. Koenderink and A.J. van Doorn. Representation of local geometry in the visual system. Biological Cybernetics, 55:367–375, 1987.CrossRefPubMedGoogle Scholar
  15. 15.
    Y. Lamdan and H.J. Wolfson. Geometric hashing: a general and efficient model-based recognition scheme. In ICCV, pages 238–249, 1988.Google Scholar
  16. 16.
    Z.D. Lan and R. Mohr. Non-parametric invariants and application to matching. Technical Report 3246, INRIA, September 1997.Google Scholar
  17. 17.
    T. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, 1994.Google Scholar
  18. 18.
    H. Murase and S.K. Nayax. Visual learning and recognition of 3D objects from appearance. IJCV, 14:5–24, 1995.CrossRefGoogle Scholar
  19. 19.
    K. Nagao. Recognizing 3D objects using photometric invariant. In ICCV, pages 480–487, 1995.Google Scholar
  20. 20.
    S.K. Nayax and R.M. Bolle. Computing reflectance ratios from an image. Pattern Recognition, 26(1):1529–1542, 1993.CrossRefGoogle Scholar
  21. 21.
    S.A. Nene and S.K. Nayar. A simple algorithm for nearest neighbor search in high dimensions. PAMI, 19(9):989–1003, 1997.Google Scholar
  22. 22.
    C.A. Poynton. Frequently asked questions about color, 1997.Google Scholar
  23. 23.
    R.P.N. Rao and D.H. Ballard. Object indexing using an iconic sparse distributed memory. In ICCV, pages 24–31, 1995.Google Scholar
  24. 24.
    B.M Romeny, L.M.J. Florack, A.H. Salden, and M.A. Viergever. Higher order differential structure of images. Image and Vision Computing, 12(6):317–325, 1994.CrossRefGoogle Scholar
  25. 25.
    C.A. Rothwell. Object Recognition Through Invariant Indexing. Oxford Science Publication, 1995.Google Scholar
  26. 26.
    B. Schiele and J.L. Crowley. Object recognition using multidimensional receptive field histograms. In ECCV, pages 610–619, 1996.Google Scholar
  27. 27.
    B. Schiele and J..L. Crowley. Probabilistic object recognition using multidimensional receptive field histogram. In ICPR, pages 50–54, 1996.Google Scholar
  28. 28.
    C. Schmid. Appariement d'images par invariants locaux de niveaux de gris. Thése de doctorat, Institut National Polytechnique de Grenoble, GRAVIR-IMAG-INRIA Rhône-Alpes, July 1996. Scholar
  29. 29.
    S.D. Shapiro. Feature space transforms for curve detection. Pattern Recognition, 10(3):129–143, 1978.CrossRefGoogle Scholar
  30. 30.
    D. Slater and G. Healey. The illumination-invariant recognition of 3D objects using color invariants. PAMI, 18(2):206–210, 1996.Google Scholar
  31. 31.
    M.J. Swain and D.H. Ballard. Color indexing. IJCV, 7(1):11–32, 1991.CrossRefGoogle Scholar
  32. 32.
    M. Turk and A. Pentland. Face recognition using eigenfaces. In CVPR, pages 586–591, 1991.Google Scholar
  33. 33.
    P. Viola. Feature-based recognition of objects. In Proceedings of the AAAI Fall Symposium Series: Machine Learning in Computer Vision: What, Why, and How?, Raleigh, North Carolina, USA, 1993.Google Scholar
  34. 34.
    A.P. Witkin. Scale-space filtering. In Proceedings of the 8th International Joint Conference on Artificial Intelligence, Karlsruhe, Germany, pages 1019–1023, 1983.Google Scholar
  35. 35.
    X. Wu and B. Bhanu. Gabor wavelets for 3D object recognition. In ICCV, pages 537–542, 1995.Google Scholar
  36. 36.
    R. Zabih and J. Woodfill. Non-parametric local transforms for computing visual correspondance. In ECCV, pages 151–158, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Roger Mohr
    • 1
  • Patrick Gros
    • 1
  • Cordelia Schmid
    • 1
  1. 1.Imag - InriaMontbonnot

Personalised recommendations