Published Articles >> Table of Contents >> Abstract

Fifth International Conference on Computer Vision (ICCV'95)   p. 434
A geometric criterion for shape-based non-rigid correspondence
H.D. Tagare, Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA
D. O'Shea, Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA
A. Rangarajan, Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.1995.466907
Send link to a friend

Abstract
A geometric criterion is developed for establishing shape based non rigid correspondence between plane curves. Unlike previous efforts, the criterion does not use rigid invariants of shape. Instead, shapes are compared non rigidly from the vantage point of the correspondence. Geometric invariants are proposed for curves whose shapes can be exactly matched by a non rigid correspondence. The invariants are based on angular deviations of convex and concave segments of the curves. Examples of correspondences between curves obtained from medical images are provided.
Back to Top Additional Information
Index Terms- computational geometry; curve fitting; medical image processing; biomedical imaging; geometric criterion; shape based nonrigid correspondence; shape-based non-rigid correspondence; shape based non rigid correspondence; plane curves; geometric invariants; angular deviations; concave segments; medical images Citation:  H.D. Tagare, D. O'Shea, A. Rangarajan, "A geometric criterion for shape-based non-rigid correspondence," iccv, p. 434,  Fifth International Conference on Computer Vision (ICCV'95),  1995