A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model

  • Umit Rusen Aktas
  • Mete Ozay
  • Aleš Leonardis
  • Jeremy L. Wyatt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)


A graph theoretic approach is proposed for object shape representation in a hierarchical compositional architecture called Compositional Hierarchy of Parts (CHOP). In the proposed approach, vocabulary learning is performed using a hybrid generative-descriptive model. First, statistical relationships between parts are learned using a Minimum Conditional Entropy Clustering algorithm. Then, selection of descriptive parts is defined as a frequent subgraph discovery problem, and solved using a Minimum Description Length (MDL) principle. Finally, part compositions are constructed using learned statistical relationships between parts and their description lengths. Shape representation and computational complexity properties of the proposed approach and algorithms are examined using six benchmark two-dimensional shape image datasets. Experiments show that CHOP can employ part shareability and indexing mechanisms for fast inference of part compositions using learned shape vocabularies. Additionally, CHOP provides better shape retrieval performance than the state-of-the-art shape retrieval methods.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-319-10578-9_37_MOESM1_ESM.pdf (2.2 mb)
Electronic Supplementary Material (PDF 2,215 KB)


  1. 1.
    Bo, L., Lai, K., Ren, X., Fox, D.: Object recognition with hierarchical kernel descriptors. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, pp. 1729–1736. IEEE Computer Society, Washington, DC (2011)Google Scholar
  2. 2.
    Bronstein, A.M., Bronstein, M.M., Bruckstein, A.M., Kimmel, R.: Analysis of two-dimensional non-rigid shapes. Int. J. Comput. Vision 78(1), 67–88 (2008)CrossRefGoogle Scholar
  3. 3.
    Cook, D.J., Holder, L.B.: Substructure discovery using minimum description length and background knowledge. J. Artif. Int. Res. 1(1), 231–255 (1994), http://dl.acm.org/citation.cfm?id=1618595.1618605 Google Scholar
  4. 4.
    Cook, D.J., Holder, L.B.: Mining Graph Data. John Wiley & Sons (2006)Google Scholar
  5. 5.
    Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: A minimum description length approach to statistical shape modeling. IEEE Trans. Med. Imag. 21(5), 525–537 (2002)CrossRefGoogle Scholar
  6. 6.
    Delong, A., Gorelick, L., Veksler, O., Boykov, Y.: Minimizing energies with hierarchical costs. Int. J. Comput. Vision 100(1), 38–58 (2012)CrossRefMATHMathSciNetGoogle Scholar
  7. 7.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  8. 8.
    Felzenszwalb, P., Schwartz, J.: Hierarchical matching of deformable shapes. In: Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8 (June 2007)Google Scholar
  9. 9.
    Ferrari, V., Tuytelaars, T., Van Gool, L.: Object detection by contour segment networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 14–28. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Fidler, S., Leonardis, A.: Towards scalable representations of object categories: Learning a hierarchy of parts. In: Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (June 2007)Google Scholar
  11. 11.
    Fidler, S., Boben, M., Leonardis, A.: Learning hierarchical compositional representations of object structure. In: Dickinson, S.J., Leonardis, A., Schiele, B., Tarr, M.J. (eds.) Object categorization computer and human perspectives, pp. 196–215. Cambridge University Press, Cambridge (2009)CrossRefGoogle Scholar
  12. 12.
    Guo, C.-E., Zhu, S.-C., Wu, Y.N.: Modeling visual patterns by integrating descriptive and generative methods. Int. J. Comput. Vision 53(1), 5–29 (2003)CrossRefGoogle Scholar
  13. 13.
    Kokkinos, I., Yuille, A.: Inference and learning with hierarchical shape models. Int. J. Comput. Vis. 93(2), 201–225 (2011)CrossRefMATHMathSciNetGoogle Scholar
  14. 14.
    Latecki, L., Lakamper, R., Eckhardt, T.: Shape descriptors for non-rigid shapes with a single closed contour. In: Proceedings of the 2000 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 424–429 (June 2000)Google Scholar
  15. 15.
    Levinshtein, A., Sminchisescu, C., Dickinson, S.J.: Learning hierarchical shape models from examples. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 251–267. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  16. 16.
    Li, H., Zhang, K., Jiang, T.: Minimum entropy clustering and applications to gene expression analysis. In: Proceedings of the 2004 IEEE Computational Systems Bioinformatics Conference, CSB 2004, pp. 142–151. IEEE Computer Society, Washington, DC (2004)Google Scholar
  17. 17.
    Ling, H., Jacobs, D.: Shape classification using the inner-distance. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 286–299 (2007)CrossRefGoogle Scholar
  18. 18.
    Nanni, L., Brahnam, S., Lumini, A.: Local phase quantization descriptor for improving shape retrieval/classification. Pattern Recogn. Lett. 33(16), 2254–2260 (2012)CrossRefGoogle Scholar
  19. 19.
    Ommer, B., Buhmann, J.M.: Learning the compositional nature of visual object categories for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 501–516 (2010)CrossRefGoogle Scholar
  20. 20.
    Raviv, D., Kimmel, R., Bruckstein, A.M.: Graph isomorphisms and automorphisms via spectral signatures. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1985–1993 (2013)CrossRefGoogle Scholar
  21. 21.
    Salakhutdinov, R., Tenenbaum, J.B., Torralba, A.: Learning with hierarchical-deep models. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1958–1971 (2013)CrossRefGoogle Scholar
  22. 22.
    Shokoufandeh, A., Macrini, D., Dickinson, S., Siddiqi, K., Zucker, S.W.: Indexing hierarchical structures using graph spectra. IEEE Trans. Pattern Anal. Mach. Intell. 27(7), 1125–1140 (2005)CrossRefGoogle Scholar
  23. 23.
    Siddiqi, K., Shokoufandeh, A., Dickinson, S.J., Zucker, S.W.: Shock graphs and shape matching. Int. J. Comput. Vision 35(1), 13–32 (1999)CrossRefGoogle Scholar
  24. 24.
    Torsello, A., Hancock, E.R.: Learning shape-classes using a mixture of tree-unions. IEEE Trans. Pattern Anal. Mach. Intell. 28(6), 954–967 (2006)CrossRefGoogle Scholar
  25. 25.
    Zhu, A.L., Chen, Y., Yuille: Learning a hierarchical deformable template for rapid deformable object parsing. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1029–1043 (2010)CrossRefGoogle Scholar
  26. 26.
    Zhu, L.L., Chen, Y., Yuille, A.: Recursive compositional models for vision: Description and review of recent work. J. Math. Imaging Vis. 41(1-2), 122–146 (2011)CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Umit Rusen Aktas
    • 1
  • Mete Ozay
    • 1
  • Aleš Leonardis
    • 1
  • Jeremy L. Wyatt
    • 1
  1. 1.School of Computer ScienceThe University of BirminghamBirminghamUK

Personalised recommendations