Learning Shape Detector by Quantizing Curve Segments with Multiple Distance Metrics

  • Ping Luo
  • Liang Lin
  • Hongyang Chao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6313)


In this paper, we propose a very efficient method to learn shape models using local curve segments with multiple types of distance metrics. Our learning approach includes two key steps: feature generation and model pursuit. In the first step, for each category, we first extract a massive number of local “prototype” curve segments from a few roughly aligned shape instances. Then we quantize these curve segments with three types of distance metrics corresponding to different shape deformations. In each metric space, the quantized curve segments are further grown (spanned) into a large number of ball-like manifolds, and each of them represents a equivalence class of shape variance. In the second step of shape model pursuit, using these manifolds as features, we propose a fast greedy learning algorithm based on the information projection principle. The algorithm is guided by a generative model, and stepwise selects the features that have maximum information gain. The advantage of the proposed method is identified on several public datasets and summarized as follows. (1) Our models consisting of local curve segments with multiple distance metrics are robust to the various shape deformations, and thus enable us to perform robust shape classification and detect shapes against background clutter. (2) The auto-generated curve-based features are very general and convenient, rather than designing specific features for each category.


Object Detection Shape Model Geodesic Distance Shape Descriptor Distance Metrics 
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.
    Belongie, S., Malik, J., Puzicha, J.: Shape Matching and Object Recognition Using Shape Contexts. TPAMI 24(4), 509–522 (2002)Google Scholar
  2. 2.
    Bai, X., et al.: Shape Band: A Deformable Object Detection Approach. In: CVPR, pp. 1335–1342 (2009)Google Scholar
  3. 3.
    Cootes, T.F., et al.: Active Shape Models - their training and application. CVIU 61, 38–59 (1995)Google Scholar
  4. 4.
    Csiszar, I., et al.: Information Theory and Statistics: A Tutorial. Commun. Inf. Theory 1(4), 417–528 (2004)CrossRefGoogle Scholar
  5. 5.
    Dalal, N., et al.: Histograms of Oriented Gradients for Human Detection. In: CVPR, vol. 1(1), pp. 886–893 (2005)Google Scholar
  6. 6.
    Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. John Wiley and Son, Chichester (1998)zbMATHGoogle Scholar
  7. 7.
    Felzenszwalb, P.F., Schwartz, J.D.: Hierarchical Matching of Deformable Shapes. In: CVPR (2007)Google Scholar
  8. 8.
    Ferrari, V., Jurie, F., Schmid, C.: From Images to Shape models for Object Detection. Intern’l Jour. of Computer Vision (2009)Google Scholar
  9. 9.
    Goodall, C.: Procrustes Methods in the Statistical Analysis of Shape. Jour. Royal Statistical Society 53, 285–339 (1991)zbMATHMathSciNetGoogle Scholar
  10. 10.
    Gu, C., Lim, J.J., Arbelaez, P., Malik, J.: Recognition using Regions. In: CVPR (2009)Google Scholar
  11. 11.
    Jiang, T., Jurie, F., Schmid, C.: Learning Shape Prior Models for Object Matching. In: CVPR, pp. 848–855 (2009)Google Scholar
  12. 12.
    Klassen, E., Srivastava, A., Mio, W., Joshi, S.: Analysis of Planar Shapes Using Geodesic Paths on Shape Spaces. IEEE Trans. PAMI 26(3), 372–383 (2004)Google Scholar
  13. 13.
    Ling, H., Jacobs, D.W.: Shape Classification Using the Inner-distance. TPAMI 29(2), 286–299 (2007)Google Scholar
  14. 14.
    Leibe, B., et al.: Combined Object Categorization and Segmentation With An Implicit Shape Model. In: ECCV Workshop, pp. 17–32 (2004)Google Scholar
  15. 15.
    Lin, L., et al.: An Empirical Study of Object Category Recognition: Sequential Testing with Generalized Samples. In: ICCV, vol. 1, pp. 419–426 (2007)Google Scholar
  16. 16.
    Lin, L., Wu, T., Xu, Z., Porway, J.: A Stochastic Graph Grammar for Compositional Object Representation and Recognition. Pattern Recognition 42(7), 1297–1307 (2009)zbMATHCrossRefGoogle Scholar
  17. 17.
    Lin, L., Liu, X., Zhu, S.C.: Layered Graph Matching with Composite Cluster Sampling. IEEE Trans. PAMI (2010)Google Scholar
  18. 18.
    McNeill, G., et al.: Hierarchical Procrustes Matching for Shape Retrieval. In: CVPR, vol. 1, pp. 885–894 (2006)Google Scholar
  19. 19.
    Ommer, B., et al.: Multi-Scale Object Detection by Clustering Lines. In: ICCV (2009)Google Scholar
  20. 20.
    Pietra, V.D., et al.: Inducing Features of Random Fields. TPAMI 19, 380–393 (1997)Google Scholar
  21. 21.
    Siddiqi, K., et al.: Shock Graphs and Shape Matching. IJCV 35(1), 13–32 (1999)CrossRefGoogle Scholar
  22. 22.
    Shotton, J., Blake, A., Cipolla, R.: Multi-Scale Categorical Object Recognition Using Contour Fragments. IEEE Tran. PAMI (2008)Google Scholar
  23. 23.
    Todorovic, S., Ahuja, N.: Unsupervised Category Modeling, Recognition, and Segmentation in Images. IEEE Tran. PAMI (2008)Google Scholar
  24. 24.
    Yao, B., Yang, X., Lin, L., Lee, M.W., Zhu, S.C.: I2T: Image Parsing to Text Description. Proceedings of IEEE (2010) (to appear)Google Scholar
  25. 25.
    Yu, X., Yi, L., Fermuller, C., Doermann, D.: Object Detection Using Shape Codebook. In: BMVC (2007)Google Scholar
  26. 26.
    Zhu, Q., et al.: Contour Context Selection for Object Detection: A set-to-set contour matching approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 774–787. Springer, Heidelberg (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ping Luo
    • 1
    • 2
  • Liang Lin
    • 1
    • 2
  • Hongyang Chao
    • 1
  1. 1.School of SoftwareSun Yat-Sen UniversityGuangzhouP.R. China
  2. 2.Lotus Hill Research InstituteP.R. China

Personalised recommendations