Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Algebraic Frames for the Perception-Action Cycle

AFPAC 1997: Algebraic Frames for the Perception-Action Cycle pp 176–189Cite as

Fractal basis functions for pattern recognition

  • Recognition of Visual Structure
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1315))

Abstract

Asynchronous fractal operators are designed for images in order to implement fractal applications by massive parallel asynchronous computing system. Assuming the convergence of the standard fractal operator to an element \(\tilde f\)which is an approximation of the original image f, it is proved that any asynchronous deterministic realization of local fractal operators is convergent to \(\tilde f\)and the stochastic realization converges to \(\tilde f\)with probability one. A new class of basis functions is defined using fractal operators designed for class representatives. Applications for object recognition and image association are presented.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. S. Amari, “Learning patterns and pattern sequences by self-organizing nets of threshold elements”, IEEE Trans. on Computer, C-21, pp. 1197–1206, 1972.

    Google Scholar 

  2. S. Amari, “Neural theory of association and concept formation”, Biological Cybernetics, 26, pp. 175–185, 1977.

    Article  PubMed  Google Scholar 

  3. S. Banach, “Sur les operations dans les ensembles abstraits et leur applications aux equations integrates”, Fundamenta Mathematica, vol.3, pp. 133–181, 1922.

    Google Scholar 

  4. J. Dugundi and A. Granas, Fixed point theory, Polish Scientific Publishers, Warszawa, 1982.

    Google Scholar 

  5. Y. Fisher, ed., Fractal Image Compression — Theory and Application, Springer Verlag (1995).

    Google Scholar 

  6. S. Haykin, Neural networks — A Comprehensive Foundation, Maxwell Macmillan International (1994).

    Google Scholar 

  7. J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Natl. Acad. Sci. USA, Biophysics, 79, pp. 2554–2558 (1982).

    Google Scholar 

  8. A. Jacquin, “Image coding based on a fractal theory of iterated contractive image transformations,” IEEE Trans. Image Processing, 1, pp. 18–30 (1992).

    Article  Google Scholar 

  9. Ferdinando Samaria and Andy Harter, “Parameterisation of a stochastic model for human face identification,” Proceedings of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota FL, December 1994.

    Google Scholar 

  10. W. Skarbek, “On convergence of affine fractal operators”, Image Processing and Communications, 1, pp. 33–41 (1995).

    Google Scholar 

  11. S. W. Smoliar and H. Zhang, “Content-Based Video Indexing and Retrieval,” IEEE Multimedia, 1, pp. 62–72, (1994).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Polish-Japanese Institute of Computer Techniques, Koszykowa 86, 02-008, Warsaw, Poland

    Wladysław Skarbek

  2. Electronics and Information Technology Department, Warsaw Univ. of Technology, Poland

    Krystian Ignasiak

Authors
  1. Wladysław Skarbek
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Krystian Ignasiak
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Gerald Sommer Jan J. Koenderink

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Skarbek, W., Ignasiak, K. (1997). Fractal basis functions for pattern recognition. In: Sommer, G., Koenderink, J.J. (eds) Algebraic Frames for the Perception-Action Cycle. AFPAC 1997. Lecture Notes in Computer Science, vol 1315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017867

Download citation

  • DOI: https://doi.org/10.1007/BFb0017867

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63517-8

  • Online ISBN: 978-3-540-69589-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation