Learning and Bayesian Shape Extraction for Object Recognition

  • Washington Mio
  • Anuj Srivastava
  • Xiuwen Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3024)


We present a novel algorithm for extracting shapes of contours of (possibly partially occluded) objects from noisy or low-contrast images. The approach taken is Bayesian: we adopt a region-based model that incorporates prior knowledge of specific shapes of interest. To quantify this prior knowledge, we address the problem of learning probability models for collections of observed shapes. Our method is based on the geometric representation and algorithmic analysis of planar shapes introduced and developed in [15]. In contrast with the commonly used approach to active contours using partial differential equation methods [12,20,1], we model the dynamics of contours on vector fields on shape manifolds.


Object Recognition Active Contour Image Model Shape Space Angle Function 
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.
    Chan, T., Shen, J., Vese, L.: Variational PDE Models in Image Processing. Notices Amer. Math. Soc. 50, 14–26 (2003)zbMATHMathSciNetGoogle Scholar
  2. 2.
    Cremers, D., Soatto, S.: A Pseudo Distance for Shape Priors in Level Set Segmentation. In: Proc. 2nd IEEE Workshop on Variational, Geometric, and Level-Set Methods in Computer Vision, Nice, France (2003)Google Scholar
  3. 3.
    Cremers, D., Tischhäuser, F., Weickert, J., Schnörr, C.: Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional. Internat. Journal Computer Vision 50, 295–313 (2002)zbMATHCrossRefGoogle Scholar
  4. 4.
    Do Carmo, M.P.: Differential Geometry of Curves and Surfaces. Prentice-Hall, Englewood Cliffs (1976)zbMATHGoogle Scholar
  5. 5.
    Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. John Wiley & Sons, Chichester (1998)zbMATHGoogle Scholar
  6. 6.
    Duta, N., Jain, A.K.: Dubuisson-Jolly, M.P.: Automatic Construction of 2D Shape Models. IEEE Trans. Pattern Analysis and Machine Intelligence 23 (2001)Google Scholar
  7. 7.
    Duta, N., Sonka, M., Jain, A.K.: Learning Shape Models from Examples Using Automatic Shape Clustering and Procrustes Analysis. In: Kuba, A., Sámal, M., Todd-Pokropek, A. (eds.) IPMI 1999. LNCS, vol. 1613, pp. 370–375. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  8. 8.
    Grenander, U.: General Pattern Theory. Oxford University Press, Oxford (1993)Google Scholar
  9. 9.
    Grenander, U., Milller, M.I.: Computational Anatomy: an Emerging Discipline. Quarterly of Applied Mathematics LVI, 617–694 (1998)Google Scholar
  10. 10.
    Holbolth, A., Kent, J.T., Dryden, I.L.: On the Relation Between Edge and Vertex Modeling in Shape Analysis. Scandinavian Journal of Statistics 29, 355–374 (2002)CrossRefGoogle Scholar
  11. 11.
    Karcher, H.: Riemann Center of Mass and Mollifier Smoothing. Comm. Pure Appl. Math. 30, 509–541 (1977)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. International Journal of Computer Vision 1, 321–331 (1988)CrossRefGoogle Scholar
  13. 13.
    Kendall, D.G.: Shape Manifolds, Procrustean Metrics and Complex Projective Spaces. Bull. London Math. Society 16, 81–121 (1984)zbMATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Kent, J.T., Dryden, I.L., Anderson, C.R.: Using Circulant Symmetry to Model Featureless Objects. Biometrika 87, 527–544 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Klassen, E., Srivastava, A., Mio, W., Joshi, S.: Analysis of Planar Shapes Using Geodesic Paths on Shape Spaces. IEEE Trans. Pattern Analysis and Machine Intelligence 26 (2004)Google Scholar
  16. 16.
    Le, H.L., Kendall, D.G.: The Riemannian Structure of Euclidean Shape Spaces: a Novel Environment for Statistics. Annals of Statistics 21, 1225–1271 (1993)zbMATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Leventon, M., Grimson, W., Faugeras, O.: Statistical Shape Infuence in Geodesic Active Contours. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (2000)Google Scholar
  18. 18.
    Miller, M.I., Younes, L.: Group Actions, Homeomorphisms, and Matching: A General Framework. International Journal of Computer Vision 41, 61–84 (2002)CrossRefGoogle Scholar
  19. 19.
    Mumford, D., Shah, J.: Optimal Approximations by Piecewise Smooth Functions and Associated Variational Problems. Comm. Pure Appl. Math. 42, 577–685 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Sethian, J.: Level Set Methods: Evolving Interfaces in Geometry, Fluid Mechanics, Computer Vision, and Material Science. Cambridge University Press, Cambridge (1996)zbMATHGoogle Scholar
  21. 21.
    Small, C.G.: The Statistical Theory of Shape. Springer, Heidelberg (1996)zbMATHGoogle Scholar
  22. 22.
    Joshi, S., Srivastava, A., Mio, W., Liu, X.: Hierarchical Organization of Shapes for Efficient Retrieval. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 570–581. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  23. 23.
    Srivastava, A., Mio, W., Klassen, E., Liu, X.: Geometric Analysis of Constrained Curves for Image Understanding. In: Proc. 2nd Workshop on Variational, Geometric and Level-Set Methods in Computer Vision, Nice, France (2003)Google Scholar
  24. 24.
    Younes, L.: Computable Elastic Distance Between Shapes. SIAM Journal of Applied Mathematics 58, 565–586 (1998)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Washington Mio
    • 1
  • Anuj Srivastava
    • 1
  • Xiuwen Liu
    • 1
  1. 1.Florida State UniversityTallahasseeUSA

Personalised recommendations