• DocumentCode
    2353329
  • Title

    Rethinking classical internal forces for active contour models

  • Author

    Perrin, Doug P. ; Smith, Christopher E.

  • Author_Institution
    Minnesota Univ., Minneapolis, MN, USA
  • Volume
    2
  • fYear
    2001
  • fDate
    2001
  • Abstract
    The classical active contour model has two basic internal forces: tension and curvature. These forces are included to provide cohe sion, equal control point spacing, and locally smooth shape. These classical internal forces have undesirable attributes that are in conflict with these original desired characteristics. Tension evenly spaces the control points, but also causes the models to collapse in weak image gradients. Curvature produces locally smooth curvature, but it does so by forcing the model toward a straight line. The paper returns to the original active contour model motivations to reformulate these internal forces. The desired properties are achieved without the introduction of unwanted model behavior A new spacing force and a new constant change in curvature force are introduced and their performance characteristics are discussed. The paper includes experimental results that demonstrate the efficacy and performance of the proposed reformulations.
  • Keywords
    computer vision; edge detection; minimisation; active contour model motivations; active contour models; classical active contour model; classical internal forces; cohesion; curvature force; equal control point spacing; internal forces; locally smooth curvature; locally smooth shape; performance characteristics; snakes; spacing force; straight line; tension; weak image gradients; Active contours; Computer science; Computer vision; Deformable models; Force control; Force measurement; Merging; Pressure measurement; Shape control;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on
  • ISSN
    1063-6919
  • Print_ISBN
    0-7695-1272-0
  • Type

    conf

  • DOI
    10.1109/CVPR.2001.991020
  • Filename
    991020