Non-rigid registration by geometry-constrained diffusion.

Per Rønsholt Andresen, Mads Nielsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    107 Downloads (Pure)

    Abstract

    Assume that only partial knowledge about a non-rigid registration is given so that certain point, curves, or surfaces in one 3D image map to certain points, curves, or surfaces in another 3D image. We are facing the aperture problem because along the curves and surfaces, point correspondences are not given. We will advocate the viewpoint that the aperture and the 3D interpolation problem may be solved simultaneously by finding the simplest displacement field. This is obtained by a geometry-constrained diffusion which yields the simplest displacement field in a precise sense. The point registration obtained may be used for growth modelling, shape statistics, or kinematic interpolation. The algorithm applies to geometrical objects of any dimensionality. We may thus keep any number of fiducial points, curves, and/or surfaces fixed while finding the simplest registration. Examples of inferred point correspondences in a longitudinal growth study of the mandible are given.
    Original languageEnglish
    Title of host publicationMedical Image Computing and Computer-Assisted Intervention - MICCAI 1999
    PublisherSpringer Verlag
    Publication date1999
    Pages533-543
    Publication statusPublished - 1999
    EventMedical Image Computing & Computer-Assisted - Cambrigde, England
    Duration: 1 Jan 1999 → …

    Conference

    ConferenceMedical Image Computing & Computer-Assisted
    CityCambrigde, England
    Period01/01/1999 → …

    Cite this