Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Deep Structure, Singularities, and Computer Vision

DSSCV 2005: Deep Structure, Singularities, and Computer Vision pp 169–180Cite as

Exploiting Deep Structure

  • Conference paper

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3753))

Abstract

Blurring an image with a Gaussian of width σ and considering σ as an extra dimension, extends the image to an Gaussian scale space (\(\mathcal{GSS}\)) image. In this \(\mathcal{GSS}\)-image the iso-intensity manifolds behave in an nicely pre-determined manner. As a result of that, the \(\mathcal{GSS}\)-image directly generates a hierarchy in the form of a binary ordered rooted tree, that can be used for segmentation, indexing, recognition and retrieval. Understanding the geometry of the manifolds allows fast methods to derive the hierarchy. In this paper we discuss the relevant geometric properties of \(\mathcal{GSS}\) images, as well as their implications for algorithms used for the tree extraction. Examples show the applicability and increased speed of the proposed method compared to traditional ones.

This work is part of the DSSCV project supported by the IST Programme of the European Union (IST-2001-35443). WWW home page: http://www.itu.dk/Internet/sw1953.asp

This is a preview of subscription content, 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   39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
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

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Damon, J.: Local Morse theory for solutions to the heat equation and Gaussian blurring. Journal of Differential Equations 115(2), 386–401 (1995)

    Article  MathSciNet  Google Scholar 

  2. Florack, L.M.J.: Image Structure. Computational Imaging and Vision Series, vol. 10. Kluwer Academic Publishers, Dordrecht (1997)

    Google Scholar 

  3. Griffin, L.D., Colchester, A.: Superficial and deep structure in linear diffusion scale space: Isophotes, critical points and separatrices. Image and Vision Computing 13(7), 543–557 (1995)

    Article  Google Scholar 

  4. Griffin, L.D., Lillholm, M. (eds.): Scale-Space 2003. LNCS, vol. 2695. Springer, Heidelberg (2003)

    MATH  Google Scholar 

  5. ter Haar Romeny, B.M.: Front-end vision and multi-scale image analysis. Computational Imaging and Vision Series, vol. 27. Kluwer Academic Publishers, Dordrecht (2003)

    Google Scholar 

  6. Iijima, T.: On the Gaussian scale-space. IEICE Japan, Trans. D E86-D(7), 1162–1164 (2003)

    Google Scholar 

  7. Kanters, F., Platel, B., Florack, L.M.J., ter Haar Romeny, B.M.: Content based image retrieval using multiscale top points. In: Griffin and Lillholm [4], pp. 33–43 (2003)

    Google Scholar 

  8. Kerckhove, M. (ed.): Scale-Space 2001. LNCS, vol. 2106. Springer, Heidelberg (2001)

    MATH  Google Scholar 

  9. Koenderink, J.J.: The structure of images. Biological Cybernetics 50, 363–370 (1984)

    Article  MathSciNet  MATH  Google Scholar 

  10. Koenderink, J.J.: A hitherto unnoticed singularity of scale-space. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(11), 1222–1224 (1989)

    Article  Google Scholar 

  11. Kuijper, A., Florack, L.M.J.: Hierarchical pre-segmentation without prior knowledge. In: Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada, July 9-12, pp. 487–493 (2001)

    Google Scholar 

  12. Kuijper, A., Florack, L.M.J.: The hierarchical structure of images. IEEE Transactions on Image Processing 12(9), 1067–1079 (2003)

    Article  MathSciNet  Google Scholar 

  13. Lifshitz, L.M., Pizer, S.M.: A multiresolution hierarchical approach to image segmentation based on intensity extrema. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(6), 529–540 (1990)

    Article  Google Scholar 

  14. Lindeberg, T.: Scale-Space Theory in Computer Vision. The Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Dordrecht (1994)

    Google Scholar 

  15. Loog, M., Duistermaat, J.J., Florack, L.M.J.: On the behavior of spatial critical points under Gaussian blurring, a folklore theorem and scale-space constraints. In: Kerckhove [8], pp. 183–192 (2001)

    Google Scholar 

  16. Schwartz, L.: Théorie des Distributions, Actualités scientifiques et industrielles; 1091,1122. vol. I, II. Publications de l’Institut de Mathématique de l’Université de Strasbourg, Paris, 1950–1951

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Image Group, IT-University of Copenhagen, Rued Langgaardsvej 7, DK-2300, Copenhagen, Denmark

    Arjan Kuijper

Authors
  1. Arjan Kuijper
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. IT University of Copenhagen, Rued Langgaardsvej 7, 2300, Copenhagen South, Denmark

    Ole Fogh Olsen

  2. Technische Universiteit Eindhoven, P.O. Box 513, 5600, Eindhoven, MB, The Netherlands

    Luc Florack

  3. Radon Institute for Computational and Applied Mathematics, Linz, Austria

    Arjan Kuijper

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kuijper, A. (2005). Exploiting Deep Structure. In: Fogh Olsen, O., Florack, L., Kuijper, A. (eds) Deep Structure, Singularities, and Computer Vision. DSSCV 2005. Lecture Notes in Computer Science, vol 3753. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11577812_15

Download citation

  • DOI: https://doi.org/10.1007/11577812_15

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-29836-6

  • Online ISBN: 978-3-540-32097-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation