Advertisement

A Hierarchical Framework for Shape Recognition Using Articulated Shape Mixtures

  • Abdullah Al Shaher
  • Edwin R. Hancock
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3211)

Abstract

This paper describes a statistical framework for recognising 2D shapes with articulated components. The shapes are represented using both geometrical and a symbolic primitives, that are encapsulated in a three layer hierarchical architecture. Each primitive is modelled so as to allow a degree of articulated freedom using a polar point distribution model that captures how the primitive movement varies over a training set. Each segment is assigned a symbolic label to distinguish its identity, and the overall shape is represented by a configuration of labels. We demonstrate how both the point-distribution model and the symbolic labels can be combined to perform recognition using the hierarchical mixture of experts algorithm. This involves recovering the parameters of the point distribution model that minimise an alignment error, and recovering symbol configurations that minimise a structural error. We apply the recognition strategy on sets of Arabic characters.

Keywords

Recognition Rate Posteriori Probability Landmark Point Hierarchical Framework Primitive Movement 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cootes, T., Taylor, C.: Combining point distribution models with shape models based on finite element analysis. Image and Vision Computing 13(5), 403–409 (1995)CrossRefGoogle Scholar
  2. 2.
    Duta, N., Jain, A., Dubuisson, P.: Learning 2d shape models. International Conference on Computer Vision and pattern Recognition 2, 8–14 (1999)Google Scholar
  3. 3.
    Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Proc. European Conf. on Computer Vision, pp. 343–356 (1996)Google Scholar
  4. 4.
    Gonzales, J., Varona, J., Roca, F., Villanueva, J.: A space: Action space for recognition and synthesis of human actions. In: 2nd IWAMDO, Spain, pp. 189–200 (2002)Google Scholar
  5. 5.
    Jordan, M., Jacobs, R.: Hierarchical mixtures of experts and theem algorithm. Neural Computation 6, 181–214 (1994)CrossRefGoogle Scholar
  6. 6.
    Heap, T., Hogg, D.: Extending the point distribution model using polar coordinates. Image and Vision Computing 14, 589–599 (1996)CrossRefGoogle Scholar
  7. 7.
    Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via theem algorithm. Journal of Royal Statistical Soc. Ser. 39, 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  8. 8.
    Hancock, E.R., Kittler, J.: Edge-labelling using dictionary-based relaxation. IEEE Transaction on PAMI 12(2), 165–181 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Abdullah Al Shaher
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.University of YorkYorkUK

Personalised recommendations