Object recognition from large structural libraries

  • Benoit Huet
  • Edwin R. Hancock
Recognition of 2D and 3D Objects
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


This paper presents a new similarity measure for object recognition from large libraries of line-patterns. The measure commences from a Bayesian consistency criterion which as been developed for locating correspondence matches between attributed relational graphs using iterative relaxation operations. The aim in this paper is to simplify the consistency measure so that it may used in a non-iterative manner without the need to compute explicit correspondence matches. This considerably reduces the computational overheads and renders the consistency measure suitable for large-scale object recognition. The measure uses robust error-kernels to gauge the similarity of pairwise attribute relations defined on the edges of nearest neighbour graphs. We use the similarity measure in a recognition experiment which involves a library of over 2000 line-patterns. A sensitivity study reveals that the method is capable of delivering a recognition accuracy of 94%. A comparative study reveals that the method is most effective when a Gaussian kernel or Huber's robust kernel is used to weight the attribute relations. Moreover, the method consistently outperforms Rucklidge's median Hausdorff distance.


  1. 1.
    Y. Lamdan and H. Wolfson, “Geometric hashing: A general and efficient model-based recognition scheme,” In, Proc. of ICCV, pp. 238–249, 1988.Google Scholar
  2. 2.
    M. Costa and L. Shapiro, “Scene analysis using appearance-based models and relational indexing,” In Proc. of ISCV, pp. 103–108, 1995.Google Scholar
  3. 3.
    C. A. Rothwell, A. Zisserman, D. Forsyth, and J. Mundy, “Canonical frames for planar object recognition,” In Proc. of ECCV, pp. 757–772, 1992.Google Scholar
  4. 4.
    Y. Landam, J. T. Schwartz, and H. J. Wolfson, “Object recognition by affine invariant matching,” in Proc. of CVPR Conf., pp. 335–344, 1988.Google Scholar
  5. 5.
    A. Evans, N. Thacker, and J. Mayhew, “The use of geometric histograms for model-based object recognition,” In Proc. of BMVC, pp. 429–438, 1993.Google Scholar
  6. 6.
    W. Rucklidge, “Locating ojects using the Hausdorff distance,” In Proc. of ICCV, pp. 457–464, 1995.Google Scholar
  7. 7.
    R. Wilson and E. R. Hancock, “Structural matching by discrete relaxation,” PAMI, vol. 19, pp. 634–648, June 1997.Google Scholar
  8. 8.
    A. Cross and E. Hancock, “Recovering perspective pose with dual step EM algorithm,” Advances in NIPS, vol. 10, 1998. MIT Press, to appear.Google Scholar
  9. 9.
    B. Huet and E. R. Hancock, “Cartographic indexing into a database of remotely sensed images,” In Proc. of WACV, pp. 8–14, Dee 1996.Google Scholar
  10. 10.
    J. Kittler and E. Hancock, “Combining evidence in probabilistic relaxation,” Int. J. of Pattern Recognition and Artificial Intelligence, vol. 3, no. 1, pp. 29–51, 1989.CrossRefGoogle Scholar
  11. 11.
    W. Christmas, J. Kittler, and M. Petrou, “Structural matching in computer vision using probabilistic relaxation,” PAMI, vol. 17, pp. 749–764, 1995.CrossRefGoogle Scholar
  12. 12.
    A. Pentland, R. Picard, and S. Sclaroff, “Photobook: Content-based manipulation of image databases,” Int. J. of Computer Vision, vol. 18, no. 3, pp. 233–254, 1996.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Benoit Huet
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations