Skip to main content
SpringerLink
Log in

Averaged Template Matching Equations

  • Conference paper
  • First Online:
Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2001)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2134))

Abstract

By exploiting an analogy with averaging procedures in fluid dynamics, we present a set of averaged template matching equations. These equations are analogs of the exact template matching equations that retain all the geometric properties associated with the diffeomor-phism group, and which are expected to average out small scale features and so should, as in hydrodynamics, be more computationally efficient for resolving the larger scale features. From a geometric point of view, the new equations may be viewed as coming from a change in norm that is used to measure the distance between images. The results in this paper represent first steps in a longer term program: what is here is only for binary images and an algorithm for numerical computation is not yet operational. Some suggestions for further steps to develop the results given in this paper are suggested.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • Abraham, R., Marsden, J. E. and Ratiu, T. S.: Manifolds, Tensor Analysis and Applications. Springer Verlag (1988)

    Google Scholar 

  • Camassa, R. and Holm D. D.: An integrable shallow water equation with peaked soli-tons. Phys. Rev. Lett. 71 (1993) 1661–1664

    Article  MATH  MathSciNet  Google Scholar 

  • Dupuis, P., Grenander, U. and Miller, M. I.: Variational problems on flows of dif-feomorphisms for image matching. Quarterly of Applied Mathematics LVI (1998) 587–600

    MathSciNet  Google Scholar 

  • Ebin, D. E., Marsden, J. E.: Groups of diffeomorphisms and the motion of an incompressible fluid. Ann. of Math. 92 (1970) 102–163

    Article  MathSciNet  Google Scholar 

  • Grenander, U. and Miller, M. I.: Computational anatomy: an emerging discipline. Quarterly of Applied Mathematics LVI (1998) 617–694

    MathSciNet  Google Scholar 

  • Hirani, A. N., Marsden, J. E. and Arvo, J.: Averaged template matching equations. California Institute of Tecnology, Computer Science Technical Report (2001)

    Google Scholar 

  • Holm, D. D., Marsden, J. E. and Ratiu, T. S.: Euler-Poincaré models of ideal fluids with nonlinear dispersion. Phys. Res. Lett. 349 (1998) 4173–4177

    Article  Google Scholar 

  • Marsden, J. E. and Ratiu, T. S.: Introduction to Mechanics and Symmetry, Second Edition. Springer Verlag (1999)

    Google Scholar 

  • Marsden, J. E., Ratiu, T. S. and Shkoller, S.: The geometry and analysis of the averaged Euler equations and a new diffeomorphism group. Geometric and Functional Analysis 10 (2000) 582–599

    Article  MATH  MathSciNet  Google Scholar 

  • Marsden, J. E. and Shkoller, S.: Global well-posedness of the isotropic LANS equations. Proc. Royal Soc. London (to appear)

    Google Scholar 

  • Miller, M. I. and Younes, L.: Group actions, homeomorphisms and matching: a general framework. Preprint (1999)

    Google Scholar 

  • Mohseni, K., Shkoller, S., Kosović, B., Marsden, J. E., Carati, D., Wray, A. and Ro-gallo, R.: Numerical Simulations of Homogeneous Turbulence using the Lagrangian-Averaged Navier-Stokes Equations. Proc. CTR summer school (2000)

    Google Scholar 

  • Mumford, D.: Unpublished note (1998)

    Google Scholar 

  • Mumford, D.: Pattern theory and vision. Questions Mathématiques en Traitement du Signal et de L’Image, Institut Henri Poincaré (1998) 7–13

    Google Scholar 

  • Ratnanather, J. T., Baigent, S. A., Mumford, D. and Miller, M. I.: Personal communication (2000)

    Google Scholar 

  • Shkoller, S.: Geometry and curvature of diffeomorphism groups with H 1 metric and mean hydrodynamics. J. Funct. Anal. 160 (1998) 337–365

    Article  MATH  MathSciNet  Google Scholar 

  • Trouvé, A.: An infinite dimensional group approach for physics based models in pattern recognition. Preprint (1995)

    Google Scholar 

  • Trouvé, A.: Diffeomorphism groups and pattern matching in image analysis. Intl. J. Comp. Vis. 28 (1998) 213–221

    Article  Google Scholar 

  • Younes, L.: Deformations, warping and object comparison. Preprint (2000)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. California Institute of Technology, Pasadena, CA, USA

    Anil N. Hirani, Jerrold E. Marsden & James Arvo

Authors
  1. Anil N. Hirani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jerrold E. Marsden
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. James Arvo
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Instituto de Telecomunicacoes and Instituto Superior Tecnico, 1049-001, Lisboa, Portugal

    Mário Figueiredo

  2. INRIA, 2004 Route des Lucioles, 06902 Sophia-Antipolis cedex, France

    Josiane Zerubia

  3. Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, 48824, USA

    Anil K. Jain

Rights and permissions

Reprints and permissions

Copyright information

© 2001 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Hirani, A.N., Marsden, J.E., Arvo, J. (2001). Averaged Template Matching Equations. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2001. Lecture Notes in Computer Science, vol 2134. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44745-8_35

Download citation

  • DOI: https://doi.org/10.1007/3-540-44745-8_35

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-42523-6

  • Online ISBN: 978-3-540-44745-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation