• DocumentCode
    2500307
  • Title

    Contour/surface registration using a physically deformable model

  • Author

    Qian, Jiang ; Mitsa, Theophano ; Hoffman, Eric A.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Iowa Univ., Iowa City, IA, USA
  • fYear
    1996
  • fDate
    21-22 Jun 1996
  • Firstpage
    114
  • Lastpage
    122
  • Abstract
    Describes a new approach of surface/contour registration based on a physically deformable model. No prior knowledge about the types of geometric transformation is required for registration. Instead, the authors´ approach views the surface as made of elastic material that will change shape in response to the applied external force. The registration of two surfaces/contours is the deformation process of one shape towards the other governed by physical laws. Before the deformation, the two shapes are roughly registered with a global affine transformation. The physically deformable model is then applied to deform one shape to match the other. The point correspondences between the two shapes are established when one shape is finally deformed to the other. In the 2D case, the model is similar to the active contour model but registration is formulated as an equilibrium problem instead of minimization problem. The result is a set of decoupled linear system equations that are easy to solve. It is also shown that, because of physical constraints imposed the authors´ model is an improved version of Burr´s (1981) dynamic contour model. Experimental results are presented to demonstrate the performance of the model
  • Keywords
    image registration; medical image processing; modelling; surface topography measurement; Burr´s dynamic contour model; applied external force; contour registration; elastic material; equilibrium problem; geometric transformation; global affine transformation; physically deformable model; shape change; surface registration; Active contours; Biomedical imaging; Cities and towns; Deformable models; Educational institutions; Image analysis; Image registration; Image segmentation; Radiology; Shape;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Mathematical Methods in Biomedical Image Analysis, 1996., Proceedings of the Workshop on
  • Conference_Location
    San Francisco, CA
  • Print_ISBN
    0-8186-7368-0
  • Type

    conf

  • DOI
    10.1109/MMBIA.1996.534063
  • Filename
    534063