Shape intrinsic fingerprints for free-form object matching

Abstract

This paper presents matching and similarity evaluation methods between two NURBS surfaces, and their application to copyright protection of digital data representing solids or NURBS surfaces. Two methods are employed to match objects: the moment and the curvature methods. The moment method uses integral properties, i.e. the volume, the principal moments of inertia and directions, to find the rigid body transformation as well as the scaling factor. The curvature method is based on the Gaussian and the mean curvatures to establish correspondence between two objects. The matching algorithms are applied to problems of copyright protection. A suspect model is aligned to an original model through the matching methods so that similarity between two models can be assessed to determine if the suspect model contains part(s) of the original model, which may be stored in an independent repository. Three types of tests, the weak, intermediate and strong tests, are proposed for similarity assessment between two objects. The weak and intermediate tests are performed at node points obtained through shape intrinsic wireframing. The strong test relies on isolated umbilical points which can be used as fingerprints of an object for supporting an ownership claim to the original model. The three tests are organized in two decision algorithms such that they produce systematic and statistical measures for a similarity decision between two objects in a hierarchical manner. Based on the systematic and statistical evaluation of similarity, a decision can be reached whether the suspect model is an illegal copy of the original model.