From Meaningful Contours to Discriminative Object Shape

  • Pradeep Yarlagadda
  • Björn Ommer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)


Shape is a natural, highly prominent characteristic of objects that human vision utilizes everyday. But despite its expressiveness, shape poses significant challenges for category-level object detection in cluttered scenes: Object form is an emergent property that cannot be perceived locally but becomes only available once the whole object has been detected and segregated from the background. Thus we address the detection of objects and the assembling of their shape simultaneously. A dictionary of meaningful contours is obtained by clustering based on contour co-activation in all training images. We seek a joint, consistent placement of all contours in an image, since placing them independently from another is not reliable due to the emergence of shape. Therefore, the characteristic object shape is learned by discovering spatially consistent configurations of all dictionary contours using maximum margin multiple instance learning. During recognition, objects are detected and their shape is explained simultaneously by optimizing a single cost function. We demonstrate the benefit of our approach on standard shape benchmarks.


Training Image Query Image Multiple Instance Learning Cluttered Scene Object Hypothesis 
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.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: CVPR (2008)Google Scholar
  2. 2.
    Carreira, J., Sminchisescu, C.: Constrained Parametric Min-Cuts for Automatic Object Segmentation. In: CVPR (2010)Google Scholar
  3. 3.
    Borenstein, E., Ullman, S.: Combined top-down/bottom-up segmentation. PAMI 30, 2109–2125 (2008)CrossRefGoogle Scholar
  4. 4.
    Shotton, J., Blake, A., Cipolla, R.: Multi-scale categorical object rrecognition using contour fragments. PAMI 30, 1270–1281 (2007)CrossRefGoogle Scholar
  5. 5.
    Opelt, A., Pinz, A., Zisserman, A.: Incremental learning of object detectors using a visual shape alphabet. In: CVPR (2006)Google Scholar
  6. 6.
    Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 4, 115–147 (1987)CrossRefGoogle Scholar
  7. 7.
    Ommer, B., Buhmann, J.: Learning the compositional nature of visual object categories for recognition. PAMI 32 (2010)Google Scholar
  8. 8.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, pp. 264–271 (2003)Google Scholar
  9. 9.
    Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV 77, 259–289 (2008)CrossRefGoogle Scholar
  10. 10.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)Google Scholar
  11. 11.
    Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: CVPR, pp. 26–33 (2005)Google Scholar
  12. 12.
    Julesz, B.: Textons, the elements of texture perception and their interactions. Nature 29(290), 91–97 (1981)CrossRefGoogle Scholar
  13. 13.
    Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: ECCV, Workshop Stat. Learn. in Comp. Vis. (2004)Google Scholar
  14. 14.
    Gall, J., Lempitsky, V.: Class-specific hough forests for object detection. In: CVPR (2009)Google Scholar
  15. 15.
    Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: CVPR (2009)Google Scholar
  16. 16.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. PAMI 32, 1627–1645 (2010)CrossRefGoogle Scholar
  17. 17.
    Yarlagadda, P., Monroy, A., Ommer, B.: Voting by Grouping Dependent Parts. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 197–210. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Gavrila, D.: A bayesian, exemplar-based approach to hierarchical shape matching. PAMI 29 (2007)Google Scholar
  19. 19.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
  20. 20.
    Toshev, A., Taskar, B., Daniilidis, K.: Object detection via boundary structure segmentation. In: CVPR, pp. 950–957 (2010)Google Scholar
  21. 21.
    Zhu, L., Chen, Y., Lin, C., Yuille, A.: Max-margin learning of hierarchical configural deformable templates (hcdt) for efficient object parsing and pose estimation. IJCV 93, 1–21 (2011)zbMATHCrossRefGoogle Scholar
  22. 22.
    Fidler, S., Leonardis, A.: Towards scalable representations of object categories: Learning a hierarchy of parts. In: CVPR (2007)Google Scholar
  23. 23.
    Ahuja, N., Todorovic, S.: Connected segmentation tree: A joint representation of region layout and hierarchy. In: CVPR (2008)Google Scholar
  24. 24.
    Kokkinos, I., Yuille, A.L.: Hop: Hierarchical object parsing. In: CVPR (2009)Google Scholar
  25. 25.
    Tu, Z., Chen, X., Yuille, A., Zhu, S.: Image parsing: Unifying segmentation, detection, and recognition, vol. 2 (2005)Google Scholar
  26. 26.
    Sala, P., Dickinson, S.: Contour Grouping and Abstraction Using Simple Part Models. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 603–616. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  27. 27.
    Ma, T., Latecki, L.: From partial shape matching through local deformation to robust global shape similarity for object detection. In: CVPR (2011)Google Scholar
  28. 28.
    Srinivasan, P., Zhu, Q., Shi, J.: Many-to-one contour matching for describing and discriminating object shape. In: CVPR (2010)Google Scholar
  29. 29.
    Liu, M., Tuzel, O.: A.Veeraraghavan, Chellappa, R.: Fast directional chamfer matching. In: CVPR (2010)Google Scholar
  30. 30.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS (2003)Google Scholar
  31. 31.
    Narasimhan, M., Bilmes, J.: A submodular-supermodular procedure with applications to discriminative structure learning. In: UAI, pp. 401–412 (2005)Google Scholar
  32. 32.
    Riemenschneider, H., Donoser, M., Bischof, H.: Using Partial Edge Contour Matches for Efficient Object Category Localization. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 29–42. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  33. 33.
    Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. IJCV 87, 284–303 (2010)CrossRefGoogle Scholar
  34. 34.
    Ommer, B., Malik, J.: Mulit-scale object detection by clustering lines. In: ICCV (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pradeep Yarlagadda
    • 1
  • Björn Ommer
    • 1
  1. 1.University of HeidelbergHeidelbergGermany

Personalised recommendations