Combining Wavelet Transform and Graph Theory for Feature Extraction and Visualization

  • Christoph Lürig
  • Roberto Grosso
  • Thomas Ertl
Part of the Eurographics book series (EUROGRAPH)


In the process of visualizing 3D MRI or CT data using techniques such as isosurfacing or direct volume rendering, one is confronted with two problems. The first one is that there is no distinction between important and unimportant data. The second one is the difficulty to find a meaningful mapping of the measured scalar values to the graphical attributes used for the visualization. These problems are addressed by the special segmentation procedure presented in this paper. The basic idea is to apply graph algorithms to find important structures and to assign multidimensional information to these structures with the help of wavelets. This additional information can be used to generate graphical attributes for rendering. Several aspects emerge from the interaction of both theoretical concepts.


Feature Vector Wavelet Transformation Wavelet Coefficient Minimal Span Tree Continuous Wavelet Transformation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    K. Berkner, C. J. G. Evertsz, and W. Berghorn. Eine lokale charakterisierung von kanten basierend auf skalierungseigenschaften von wavelet-transfomationen. In Carl J.G. Evertsz, editor,Conference Guide Visualisierung- Dynamik und Kom- plexität, September 1995.Google Scholar
  2. 2.
    A. Bijaoui. Partial reconstruction and astronomical image inventory by the wavelet transform. InProceedings ICIAP 1993, 1993.Google Scholar
  3. 3.
    J. Canny. A computational approach to edge detection.IEEE Trans. Patt. Anal. Machine Inteli, PAMI-8: 679–698, 1986.Google Scholar
  4. 4.
    H. Edelsbrunner and E. P. Mücke. Three dimensional alpha shapes.ACM Transactions on Graphics, 13 (1): 43–72, January 1994.MATHCrossRefGoogle Scholar
  5. 5.
    J.A.F Leite and E. R. Hacock. Statistically combining and refining multi-channel information. InProceedings ICIAP 1993, 1993.Google Scholar
  6. 6.
    M. Levoy. Display of surface from volume data.IEEE Computer Graphics and Applications, 8 (3): 29–37, 1990.CrossRefGoogle Scholar
  7. 7.
    S. Mallat and W.L. Hwang. Singularity detection and processing with wavelets. Technical report, Courant Institute of Mathematical Sciences New York University, march 1991.Google Scholar
  8. 8.
    S. Mallat and S. Zhong. Characterization of signals from multiscale edges.IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(7):710–732, Juli 1992.CrossRefGoogle Scholar
  9. 9.
    S. Mallat and S. Zhong. Wavelet transform maxima and multiscale edges. InWavelets and their Applications. Boston: Jones and Bartlett Publication, 1992.Google Scholar
  10. 10.
    R. Westermann. Compression domain rendering of time-resolved volume data. InIEEE Visualization 1995 Conference Proceedings, pages 51–58, 1995.Google Scholar
  11. 11.
    A. Witkin. Scale space filtering. InProc. Int. Joint Conf. Artificial Intell., 1983.Google Scholar
  12. 12.
    C. T. Zahn. Graph-theoretical methods for detecting and describing gestalt cluster.IEEE Transations on Computers, C-20(l): 68–86, 1971.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wein 1997

Authors and Affiliations

  • Christoph Lürig
    • 1
  • Roberto Grosso
    • 1
  • Thomas Ertl
    • 1
  1. 1.Computer Graphics GroupUniversity of ErlangenErlangenGermany

Personalised recommendations