Contour Grouping and Abstraction Using Simple Part Models

  • Pablo Sala
  • Sven Dickinson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


We address the problem of contour-based perceptual grouping using a user-defined vocabulary of simple part models. We train a family of classifiers on the vocabulary, and apply them to a region oversegmentation of the input image to detect closed contours that are consistent with some shape in the vocabulary. Given such a set of consistent cycles, they are both abstracted and categorized through a novel application of an active shape model also trained on the vocabulary. From an image of a real object, our framework recovers the projections of the abstract surfaces that comprise an idealized model of the object. We evaluate our framework on a newly constructed dataset annotated with a set of ground truth abstract surfaces.


Perceptual Grouping Active Shape Model Image Contour Abstract Part Initial Edge 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhu, Q., Song, G., Shi, J.: Untangling cycles for contour grouping. In: ICCV (2007)Google Scholar
  2. 2.
    Wang, J., Gu, E., Betke, M.: Mosaicshape: Stochastic region grouping with shape prior. In: CVPR (2005)Google Scholar
  3. 3.
    Stahl, J., Wang, S.: Globally optimal grouping for symmetric boundaries. In: CVPR (2006)Google Scholar
  4. 4.
    Jacobs, D.W.: Robust and efficient detection of salient convex groups. PAMI 18, 23–37 (1996)Google Scholar
  5. 5.
    Estrada, F., Jepson, A.: Perceptual grouping for contour extraction. In: ICPR (2002)Google Scholar
  6. 6.
    Lindeberg, T.: Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention. IJCV 11, 283–318 (1993)CrossRefGoogle Scholar
  7. 7.
    Pentland, A.P.: Automatic extraction of deformable part models. IJCV 4, 107–126 (1990)CrossRefGoogle Scholar
  8. 8.
    Pilu, M., Fisher, R.: Model-driven grouping and recognition of generic object parts from single images. In: ISIRS, Lisbon, Portugal (1996)Google Scholar
  9. 9.
    Liu, L., Sclaroff, S.: Deformable model-guided region split and merge of image regions. IVC 22, 343–354 (2004)Google Scholar
  10. 10.
    Sala, P., Dickinson, S.: Model-based perceptual grouping and shape abstraction. In: POCV, Anchorage, Alaska, pp. 1–8 (2008)Google Scholar
  11. 11.
    Buchin, K., Knauer, C., Kriegel, K., Schulz, A., Seidel, R.: On the number of cycles in planar graphs. In: Lin, G. (ed.) COCOON 2007. LNCS, vol. 4598, pp. 97–107. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Tiernan, J.C.: An efficient search algorithm to find the elementary circuits of a graph. Commun. ACM 13, 722–726 (1970)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models - their training and application. CVIU 61, 38–59 (1995)Google Scholar
  14. 14.
    Douglas, D., Peucker, T.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. CC 10, 112–122 (1973)Google Scholar
  15. 15.
    Tax, D., Duin, R.: Data description in subspaces. In: ICPR, vol. 2, pp. 672–675 (2000)Google Scholar
  16. 16.
    Mount, D.M., Arya, S.: ANN: A library for approximate nearest neighbor searching (2006),
  17. 17.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pablo Sala
    • 1
  • Sven Dickinson
    • 1
  1. 1.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations