Modelling of Shapes without Landmarks

  • Felix Wehrmann
  • Ewert Bengtsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

The complexity in variation that objects are provided with motivates to consider learning strategies when modeling their shape. This paper evaluates auto-associative neural networks and their application to shape analysis. Previously, such networks have been considered in connection with ‘point distribution models’ for describing two-dimensional contours in a statistical manner. This paper suggests an extension of this idea to achieve a more flexible model that is independent of landmarks.

Keywords

Feature Space Shape Space Trained Network Active Shape Model Shape Data 
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.

References

  1. 1.
    David P. Casasent and Leonard M. Neiberg. Classifier and shift-invariant automatic target recognition neural networks. Neural networks, 8(7–8):1117–1129, 1995.CrossRefGoogle Scholar
  2. 2.
    T.F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham. Active shape models—their training and application. Computer vision and image understanding, 61(1):38–59, 1995.CrossRefGoogle Scholar
  3. 3.
    Daniel Freedman. Efficient simplicial reconstructions of manifolds from their samples. IEEE transactions on pattern analysis and machine intelligence, 24(10):1349–1357, October 2002.CrossRefGoogle Scholar
  4. 4.
    Michael A. Sipe, David P. Casasent, and Leonard M. Neiberg. Feature space trajectory representation for active vision. SPIE, 1997.Google Scholar
  5. 5.
    P.D. Sozou, T.F. Cootes, C.J. Taylor, and E.C. Di Mauro. Non-linear generalization of point distribution models using a multi-layer perceptron. Image and Vision Computing, 13(5):451–457, June 1995.CrossRefGoogle Scholar
  6. 6.
    P.D. Sozou, T.F. Cootes, C.J. Taylor, and E.C. Di Mauro. Non-linear point distribution modelling using a multi-layer perceptron. Image and Vision Computing, 15(6):457–463, 1997.CrossRefGoogle Scholar
  7. 7.
    Lawrence H. Staib and James S. Duncan. Boundary finding with parametrically deformable models. IEEE transactions on pattern analysis and machine intelligence, 14(11):1061–1075, November 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Felix Wehrmann
    • 1
  • Ewert Bengtsson
    • 1
  1. 1.Uppsala UniversityUppsalaSweden

Personalised recommendations