Comparison of Two Multi-Scale Approaches to Edge Detection in Medical Images

  • Wolfgang Beil
  • H. Siegfried Stiehl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 905)


Based on an image model of smooth regions separated by scaled discontinuities we compare two multi-scale approaches to the problem of edge detection and characterization in two-dimensional images from X-ray (CT) and magnetic resonance tomography (MR). Both approaches have been evaluated and compared on both synthetic images reassembling characteristic properties of tomograms and real MR images from the human brain.


Edge Detection Transition Width Synthetic Image Step Edge Compute Tomogram 
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.
    Back, S., Neumann, H., Stiehl, H.S.: On Segmenting Computed Tomograms. in: H.U. Lemke, M.L. Rhodes, C.C. Jaffee, R. Felix (Eds.) Proc. 3rd International Symposium on Computer Assisted Radiology CAR’89, Springer Berlin (1989) 691696Google Scholar
  2. 2.
    Beil, W., Ottenberg, K., Stiehl, H.S.: Towards Automatic Segmentation of Two-Dimensional Brain Tomograms. in: L. Beolchi, M.H. Kuhn (Eds.) Medical Imaging–Analysis of Multimodality 2D/3D Images, Studies in Health Technology and Informatics, IOS Press 19 (1994) 158–174Google Scholar
  3. 3.
    Neumann, H., Ottenberg, K.: Estimating attributes of smooth signal transitions from scale-space. Proc. llth IAPR Int. Conf. on Pattern Recognition (ICPR-92), Le Hague III (1992) 754–758Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Wolfgang Beil
    • 1
  • H. Siegfried Stiehl
    • 1
  1. 1.FB Informatik, AB KOGSUniversität HamburgHamburgGermany

Personalised recommendations