Finding Object Categories in Cluttered Images Using Minimal Shape Prototypes

  • Johan Thuresson
  • Stefan Carlsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


We present an algorithm for recognizing object categories as opposed to specific instances, based on matching prototypical object shapes to gray-level images. The central part of the algorithm is the establishment of correspondence between prototype template and image based on finding qualitative shape invariants in the form of order types of sets of points and lines. A central problem of any matching algorithm like this is the rejection of background and foreground clutter in the image resulting in erroneous matches. By deforming the prototype and iterating the computation of correspondence we reject outliers and improve the quality of the matching. Experimental results in terms of locating examples of specific object classes in real gray-level images are presented. The results demonstrate the robustness of the algorithm and make it an interesting candidate for any categorical recognition system such as database indexing.


Object recognition shape correspondence 


  1. 1.
    Belongie S. and Malik J. Matching with Shape Contexts Proc. 8:th International Conference on Computer Vision (ICCV 2001)Google Scholar
  2. 2.
    Bremermann H. J. Cybernetic Functionals and Fuzzy Sets. IEEE Systems, Man and Cybernetics Group Annual Symposium, pages 248–254, 1971.Google Scholar
  3. 3.
    Burr D. J., Elastic Matching of Line Drawings, IEEE Trans. on Pattern Analysis and Machine Intelligence, 3, No. 6, pp. 708–713, November (1981)CrossRefGoogle Scholar
  4. 4.
    Carlsson. S, “Order Structure, Correspondence and Shape Based Categories”, International Workshop on Shape Contour and Grouping, Torre Artale, Sicily, May 26–30 1998, Springer LNCS 1681 (1999)CrossRefGoogle Scholar
  5. 5.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J., Active Shape Models: Their Training and Application, CVIU(61), No. 1, January 1995, pp. 38–59.Google Scholar
  6. 6.
    Jain A. K, Fellow, IEEE, Zhong Y, and Lakshmanan S.: Object Matching Using Deformable Templates. IEEE Transaction on Pattern Analysis and Machinge Intelligence, Vol. 18, No. 3, MarchGoogle Scholar
  7. 7.
    Lamdan Y., Schwartz, and. Wolfson, Object recognition by affine invariant matching. In: Proc. CVPR-88, pp. 335–344. (1988)Google Scholar
  8. 8.
    Sclaroff S., Deformable Prototypes for Encoding Shape Categories in Image Databases, PR(30), pp. 627–641. No. 4, April (1997)Google Scholar
  9. 9.
    Recognizing and Tracking Human Action J. Sullivan and S. Carlsson, Proc 7:th European Conference on Computer Vision (ECCV), Copenhagen, Denmark 2002. (PDF )Google Scholar
  10. 10.
    Yuille, A.L., Deformable Templates for Face Recognition, CogNeuro(3), No. 1, 1991, pp. 59–70.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Johan Thuresson
    • 1
  • Stefan Carlsson
    • 1
  1. 1.Numerical Analysis and Computing ScienceRoyal Institute of Technology, (KTH)StockholmSweden

Personalised recommendations