Skip to main content
Springer Nature Link
Log in

Beyond standard regularization theory

  • Low Level Processing II
  • Conference paper
  • First Online:
Computer Analysis of Images and Patterns (CAIP 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1296))

Included in the following conference series:

  • 137 Accesses

Abstract

A set of local interaction field are suggested to replace the δ error term in usual regularization approaches. These local fields bring some computational and conceptual benefits. A set of local oriented position pinning fields and orientation tuning fields are suggested to use local position and orientation correlations directly in regularization. Some simple experiments show that these generalizations are useful in many cases.

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.

Similar content being viewed by others

References

  1. Poggio, T., Girosi, F.: Regularization algorithms for learning that are equivalent to multilayer networks. Science 24 (1990) 978–982

    Google Scholar 

  2. Li, S. Z.: Markov Random Field Modeling in Computer Vision. Springer-Verlag 1995

    Google Scholar 

  3. Poggio,T.: A theory of how the brain might work. Cold Spring Harbor Sym. on Quantitative Bio. (1990)978–982

    Google Scholar 

  4. Zhiyong Yang, Songde Ma: Local Interaction Fields and Adaptive Regularizers For Surface Reconstruction and Image Relaxation. Technical Report, NLPR, Inst. of Automation, Chinese Acad. of Sci.(1996)

    Google Scholar 

  5. Safran, S. A.: Statistical Thermodynamics of Surfaces, Interfaces, and Membranes. Addison-Wesley Pub. Com.(1994)

    Google Scholar 

  6. Zhiyong Yang, Songde Ma: Combine local oriented position and orientation correlations with regularization. Technical Report, NLPR, Inst. of Automation, Chinese Acad. of Sci. (1996)

    Google Scholar 

  7. David, C., S.W. Zucker, Potentials, valleys, and dynamic global coverings. Int. J. Computer Vision 5 (1990) 219–238

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, P. O. Box 2728, 100080, Beijing, China

    Zhiyong Yang & Songde Ma

Authors
  1. Zhiyong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Songde Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Gerald Sommer Kostas Daniilidis Josef Pauli

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yang, Z., Ma, S. (1997). Beyond standard regularization theory. In: Sommer, G., Daniilidis, K., Pauli, J. (eds) Computer Analysis of Images and Patterns. CAIP 1997. Lecture Notes in Computer Science, vol 1296. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63460-6_129

Download citation

  • DOI: https://doi.org/10.1007/3-540-63460-6_129

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63460-7

  • Online ISBN: 978-3-540-69556-1

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics