Scale and Rotation Invariance of the Evidence Accumulation-Based Line Detection Algorithm

  • Leszek J. Chmielewski
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 30)


The scale and rotation invariance properties of a recently proposed algorithm, using the fuzzy evidence accumulation principle, for finding lines (ridges) of non-parametric shapes is analysed. The proposed modifications consist in scaling the accumulated value with the inverse of the line width and further fuzzifying the accumulation process — along the line width. Good invariance properties received are tested on artificial images and confirmed on real-life mammographic images.


  1. 1.
    Chmielewski L (2004) Detection of non-parametric lines by evidence accumulation: Finding blood vessels in mammograms. In: Proc ICCVG 2004, vol of Computational Imaging and Vision. Springer. In print.Google Scholar
  2. 2.
    Chmielewski L (2005) Specification of the evidence accumulation-based line detection algorithm. In: Proc CORES 2005, vol of Advances in Soft Computing. Springer. (In the same volume.)Google Scholar
  3. 3.
    Zwiggelaar R, Astley SM et al. (2004) Linear structures in mammographic images: detection and classification. IEEE Trans Med Imag 23(9):1077–1086CrossRefGoogle Scholar
  4. 4.
    Suckling J, Parker J et al. (1994) The Mammographic Images Analysis Society digital mammogram database. In: Gale AG, Astley SM et al. (eds) Digital Mammography, vol 1069 of Excerpta Medica International Congress Series 375–378 ( Scholar
  5. 5.
    Zwiggelaar R, Boggis CRM (2001) Classification of linear structures in mammographic images. In: Proc Conf Med Image Underst Analysis 2001 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Leszek J. Chmielewski
    • 1
  1. 1.Institute of Fundamental Technological ResearchPASWarsawPoland

Personalised recommendations