Research Information System
COMPUTER VISION AND IMAGE UNDERSTANDING, vol.79, no.2, pp.267-280, 2000 (SCI-Expanded)
A local-symmetry-based representation for shapes in arbitrary dimensions and a method for its computation are presented. The method depends on analyzing the Hessian of a specific boundaryness function, v, which is computed as the minimizer of an energy functional. The method is basically a generalized ridge finding scheme in which the ridges are defined in terms of the orbit of the gradient vector del v under the action of the Hessian of v. Once the ridges are determined, the local extrema of the magnitude of the gradient of v along the level hypersurfaces of v are used for the classification of the ridges. For the two-dimensional case, the representation reduces to the representation presented by Tari, Shah, and Pien (1997, Comput. Vision Image Understanding 66, 133-146). (C) 2000 Academic Press.