Advertisement

Multi-scale Singularity Trees: Soft-Linked Scale-Space Hierarchies

  • Kerawit Somchaipeng
  • Jon Sporring
  • Sven Kreiborg
  • Peter Johansen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3459)

Abstract

We consider images as manifolds embedded in a hybrid of a high dimensional space of coordinates and features. Using the proposed energy functional and mathematical landmarks, images are partitioned into segments. The nesting of image segments occurring at catastrophe points in the scale-space is used to construct image hierarchies called Multi-Scale Singularity Trees (MSSTs). We propose two kinds of mathematical landmarks: extrema and saddles. Unlike all other similar methods proposed hitherto, our method produces soft-linked image hierarchies in the sense that all possible connections are suggested along with their energies. The information added makes possible for directly estimating the stability of the connection and hence the costs of transitions. Aimed applications of MSSTs include multi-scale pre-segmentation, image matching, sub-object extraction, and hierarchical image retrieval.

Keywords

Critical Path Image Match Creation Event Tree Edit Distance Computer Vision Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Iijima, T.: Basic theory on normalization of a pattern (in case of typical one-dimensional pattern). Bulletin of Electrotechnical Laboratory 26, 368–388 (1962) (in Japanese)Google Scholar
  2. 2.
    Witkin, A.P.: Scale–space filtering. In: Proc. 8th Int. Joint Conf. on Artificial Intelligence (IJCAI 1983), Karlsruhe, Germany, vol. 2, pp. 1019–1022 (1983)Google Scholar
  3. 3.
    Koenderink, J.J.: The Structure of Images. Biological Cybernetics 50, 363–370 (1984)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Weickert, J., Zuiderveld, K.J., ter Haar Romeny, B.M., Niessen, W.J.: Parallel implementations of AOS schemes: A fast way of nonlinear diffusion filtering. In: Proceedings of the 4th International Conference on Image Processing, Santa Barbara, CA, USA, vol. 3, pp. 396–399. IEEE Computer Society Press, Los Alamitos (1997)CrossRefGoogle Scholar
  5. 5.
    Deriche, R.: Recursively Implementing the Gaussian and its Derivatives. In: Srinivasan, V., Heng, O.S., Hock, A.Y. (eds.) Proceedings of the 2nd Singapore International Conference on Image Processing, pp. 263–267. World Scientific, Singapore (1992)Google Scholar
  6. 6.
    van Vliet, L., Young, I., Verbeek, P.: Recursive Gaussian Derivative Filters. In: Proceedings of the 14th International Conference on Pateern Recognition ICPR 1998, Brisbane, Australia, vol. 1, pp. 509–514. IEEE Computer Society Press, Los Alamitos (1998)Google Scholar
  7. 7.
    Damon, J.: Local Morse theory for Gaussian blurred functions. In: Sporring, J., Nielsen, M., Florack, L., Johansen, P. (eds.) Gaussian Scale-Space Theory, pp. 147–163. Kluwer Academic Publishers, Dordrecht (1997)Google Scholar
  8. 8.
    Somchaipeng, K., Sporring, J., Kreiborg, S., Johansen, P.: Software for Extracting Multi-Scale Singularity Trees. Technical report, Deliverable No.8, DSSCV, IST-2001-35443 (2003)Google Scholar
  9. 9.
    Lifshitz, L.M., Pizer, S.M.: A multiresolution hierarchical approach to image segmentation based on intensity extrema. IEEE Transaction on Pattern Analysis and Machine Intelligence 12, 529–541 (1990)CrossRefGoogle Scholar
  10. 10.
    Kuijper, A.: The deep structure of Gaussian scale space images. PhD thesis, Image Sciences Institute, Institute of Information and Computing Sciences, Faculty of Mathematics and Computer Science, Utrecht University (2002)Google Scholar
  11. 11.
    Platel, B.: Multiscale Hierarchical Segmentation. Technical Report BMT-Report no. 2002-04, Department of BioMedical Engineering, Technical Universitet of Eindhoven (2002)Google Scholar
  12. 12.
    Olsen, O.F., Nielsen, M.: Multi-scale gradient magnitude watershed segmentation. In: Del Bimbo, A. (ed.) ICIAP 1997. LNCS, vol. 1310, pp. 6–13. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  13. 13.
    Somchaipeng, K., Sporring, J., Kreiborg, S., Johansen, P.: Some Transitions of Extrema-Based Multi-Scale Singularity Trees. Technical report, DSAGM 2004, Dept. of Computer Science, University of Copenhagen, DIKU (2004)Google Scholar
  14. 14.
    Somchaipeng, K., Sporring, J., Kreiborg, S., Johansen, P.: Report on Assessment of MSSTs for 3D Matching Application. Technical report, Deliverable No.21, DSSCV, IST-2001-35443 (2004)Google Scholar
  15. 15.
    Kimmel, R., Sochen, N., Malladi, R.: From High Energy Physics to Low Level Vision. In: Scale-Space Theory in Computer Vision, Utrecht, The Natherlands (1997)Google Scholar
  16. 16.
    van Ginneken, B., ter Haar Romeny, B.M.: Applications of locally orderless images. In: Scale Space 1999 (1999)Google Scholar
  17. 17.
    Arbelaez, P.A., Cohen, L.D.: The Extrema Edges. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 180–195. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  18. 18.
    Sethian, J.A.: Fast Marching Methods. SIAM Review 41, 199–235 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Samaria, F., Harter, A.: Parameterisation of a Stochastic Model for Human Face Identification. In: Proceedings of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota FL (December 1994)Google Scholar
  20. 20.
    Platel, B., Florack, L.M.J., Kanters, F.M.W., Balmachnova, E.G.: Using Multiscale Top Points in Image Matching (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Kerawit Somchaipeng
    • 1
    • 2
  • Jon Sporring
    • 2
  • Sven Kreiborg
    • 1
  • Peter Johansen
    • 2
  1. 1.3D-Lab, School of Dentistry, Dept. of Pediatric DentistryUniversity of CopenhagenCopenhagen NDenmark
  2. 2.Dept. of Computer ScienceUniversity of CopenhagenCopenhagen NDenmark

Personalised recommendations