Skip to main content
SpringerLink
Log in

A neural network energy minimization approach to approximation of 2-dimensional shapes

  • Posters
  • Conference paper
  • First Online:
Book cover Computer Analysis of Images and Patterns (CAIP 1995)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 970))

Included in the following conference series:

  • 155 Accesses

Abstract

We introduce a novel method for approximating boundaries of two-dimensional shapes using a neural network energy minimization approach. Design of the energy function allows control over the behavior of the system, which ultimately determines whether each point along the perimeter is or is not a vertex. Shapes are approximated with straight segments, circular arcs, and spiral arcs. The procedure is independent of object rotation. The method is evaluated on various shapes.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Freeman, H.: Shape Description Via the Use of Critical Points. Proc. of IEEE Comp. Soc. Conf. on Pattern Recognition and Image Proc. PRIP-77, (1977) 168–174

    Google Scholar 

  2. Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and Bayesian Restoration of Images. IEEE Transactions on PAMI 6 (1984) 721–741

    Google Scholar 

  3. Hopfield, J.: Proc. Nat. Academy of Sciences USA, 81 (1984) 3088–3092

    Google Scholar 

  4. Hopfield, J., Tank, D.,: Biological Cybernetics 52, (1985) 141–152

    Google Scholar 

  5. Koch, C., Marroquin, J., Yuille, A.: Analog neuronal networks in early vision. Proceedings of the National Academy of Sciences, USA, 83 (June 1986), 4263–4267

    Google Scholar 

  6. Ramer, U.: An Iterative Procedure for the Polygonal Approximation of Plane Curves. Computer Graphics and Image Processing 1 no. 3 (1972) 244–256

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Artificial Intelligence and Computer Science, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, 466, Nagoya, Japan

    Todd Law, Hidenori Itoh & Hirohisa Seki

Authors
  1. Todd Law
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hidenori Itoh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hirohisa Seki
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Václav Hlaváč Radim Šára

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Law, T., Itoh, H., Seki, H. (1995). A neural network energy minimization approach to approximation of 2-dimensional shapes. In: Hlaváč, V., Šára, R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60268-2_383

Download citation

  • DOI: https://doi.org/10.1007/3-540-60268-2_383

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60268-2

  • Online ISBN: 978-3-540-44781-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation