Spectral Methods for View-Based 3-D Object Recognition Using Silhouettes

  • Diego Macrini
  • Ali Shokoufandeh
  • Sven Dickinson
  • Kaleem Siddiqi
  • Steven Zucker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)


The shock graph is an emerging shape representation for object recognition, in which a 2-D silhouette is decomposed into a set of qualitative parts, captured in a directed acyclic graph. Although a number of approaches have been proposed for shock graph matching, these approaches do not address the equally important indexing problem. We extend our previous work in both shock graph matching and hierarchical structure indexing to propose the first unified framework for view-based 3-D object recognition using shock graphs. The heart of the framework is an improved spectral characterization of shock graph structure that not only drives a powerful indexing mechanism (to retrieve similar candidates from a large database), but also drives a matching algorithm that can accommodate noise and occlusion. We describe the components of our system and evaluate its performance using both unoccluded and occluded queries. The large set of recognition trials (over 25,000) from a large database (over 1400 views) represents one of the most ambitious shock graph-based recognition experiments conducted to date. This paper represents an expanded version of [12].


Object Recognition Directed Acyclic Graph Model Node Query Graph Maximum Weight Match 
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.
    J. August, K. Siddiqi, and S. W. Zucker. Ligature instabilities in the perceptual organization of shape. Computer Vision and Image Understanding, 76(3):231–243, 1999.CrossRefGoogle Scholar
  2. 2.
    R. Brooks. Model-based 3-D interpretations of 2-D images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(2):140–150, 1983.Google Scholar
  3. 3.
    M. Cyr and B. Kimia. 3d object recognition using shape similarity-based aspect graph. In Proceedings, ICCV, Vancouver, B.C., 2001.Google Scholar
  4. 4.
    P. Dimitrov, C. Phillips, and K. Siddiqi. Robust and efficient skeletal graphs. In IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, June 2000.Google Scholar
  5. 5.
    P. Flynn and A. Jain. 3D object recognition using invariant feature indexing of interpretation tables. CVGIP:Image Understanding, 55(2):119–129, March 1992.Google Scholar
  6. 6.
    H. Gabow, M. Goemans, and D. Williamson. An efficient approximate algorithm for survivable network design problems. Proc. of the Third MPS Conference on Integer Programming and Combinatorial Optimization, pages 57–74, 1993.Google Scholar
  7. 7.
    D. Huttenlocher and S. Ullman. Recognizing solid objects by alignment with an image. International Journal of Computer Vision, 5(2):195–212, 1990.CrossRefGoogle Scholar
  8. 8.
    Norio Katayama and Shin’ichi Satoh. The sr-tree: an index structure for high-dimensional nearest neighbor queries. In Proceedings of the 1997 ACM SIGMOD international conference on Management of data, pages 369–380. ACM Press, 1997.Google Scholar
  9. 9.
    Y. Lamdan, J. Schwartz, and H. Wolfson. Affine invariant model-based object recognition. IEEE Transactions on Robotics and Automation, 6(5):578–589, October 1990.Google Scholar
  10. 10.
    L. Lovász and J. Pelicán. On the eigenvalues of a tree. Periodica Math. Hung., 3:1082–1096, 1970.Google Scholar
  11. 11.
    D. Lowe. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Norwell, MA, 1985.Google Scholar
  12. 12.
    D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker. View-based 3-D object recognition using shock graphs. In Proceedings, Internal Conference on Pattern Recognition, Quebec City, August 2002.Google Scholar
  13. 13.
    H. Murase and S. Nayar. Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision, 14:5–24, 1995.CrossRefGoogle Scholar
  14. 14.
    M. Pelillo, K. Siddiqi, and S. Zucker. Matching hierarchical structures using association graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(11):1105–1120, November 1999.Google Scholar
  15. 15.
    T. Sebastian, P. Klein, and B. Kimia. Recognition of shapes by editing shock graphs. In Proceedings, ICCV, Vancouver, B.C., 2001.Google Scholar
  16. 16.
    A. Shokoufandeh and S. Dickinson. A unified framework for indexing and matching hierarchical shape structures. In Proceedings, 4th International Workshop on Visual Form, Capri, Italy, May 28–30 2001.Google Scholar
  17. 17.
    A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg. The representation and matching of qualitative shape at multiple scales. In Proceedings, ECCV, Copenhagen, May 2002.Google Scholar
  18. 18.
    A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker. Indexing using a spectral encoding of topological structure. In Proceedings, IEEE CVPR, pages 491–497, Fort Collins, CO, June 1999.Google Scholar
  19. 19.
    K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker. Shock graphs and shape matching. International Journal of Computer Vision, 30:1–24, 1999.Google Scholar
  20. 20.
    Kaleem Siddiqi and Benjamin B. Kimia. A shock grammar for recognition. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 507–513, 1996.Google Scholar
  21. 21.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71–86, 1991.CrossRefGoogle Scholar
  22. 22.
    S. Ullman and R. Basri. Recognition by linear combinations of models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10):992–1006, October 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Diego Macrini
    • 1
  • Ali Shokoufandeh
    • 2
  • Sven Dickinson
    • 3
  • Kaleem Siddiqi
    • 4
  • Steven Zucker
    • 5
  1. 1.Department of Computer ScienceUniversity of TorontoCanada
  2. 2.Department of Mathematics and Computer ScienceDrexel UniversityUSA
  3. 3.Department of Computer ScienceUniversity of TorontoCanada
  4. 4.Centre for Intelligent Machines School of Computer ScienceMcGill UniversityUSA
  5. 5.Center for Computational Vision and ControlYale UniversityUSA

Personalised recommendations