Abstract: A three-dimensional model of a reconstructed bone framework is obtained using an iterative, surface interpolating algorithm. A reference and a target three-dimensional model are provided. The reference model is non-rigidly registered to the target model based upon positional constraints, so as to produce a registered reference model. An initial reconstructed model is set as the registered reference model. A first correspondence search is iteratively conducted to identify a first set of corresponding points on the reconstructed and target models. During each iteration, the reconstructed model is incrementally and non-rigidly registered to the target model based upon the corresponding points. A second correspondence search is conducted to identify a second set of corresponding points on the reconstructed and target models.

Abstract: A three-dimensional model of a reconstructed bone framework is obtained using an iterative, surface interpolating algorithm. A reference and a target three-dimensional model are provided. The reference model is non-rigidly registered to the target model based upon positional constraints, so as to produce a registered reference model. An initial reconstructed model is set as the registered reference model. A first correspondence search is iteratively conducted to identify a first set of corresponding points on the reconstructed and target models. During each iteration, the reconstructed model is incrementally and non-rigidly registered to the target model based upon the corresponding points. A second correspondence search is conducted to identify a second set of corresponding points on the reconstructed and target models.

Abstract: A method and system for detection of bone fractures using image processing of a digitized x-ray image.

Abstract: A method of polygonizing an object calculates indicators that points within a set (Q) of points within three space representing the object likely lie near a surface discontinuity of the object. A global mesh is formed around a point that likely does not lie near a surface discontinuity (i.e. a reliable point). Local meshes are formed about reliable points on the frontier of this global mesh. Each local mesh is combined with the global mesh, thereby adding to the global mesh and advancing the frontier. Once a local mesh has been formed about each reliable point on the frontier and added to the global mesh, a local mesh may be formed about a point on the frontier that is more likely to lie near a surface discontinuity. The formation of local meshes can be repeated until no frontiers are left, or until all points have been added to the global mesh.

Abstract: A method and apparatus matches texture patterns in a way that is invariant to the intensities, scales, and orientations of the texture patterns. The texture matching apparatus includes a texture feature extractor, a feature transformer, and an image ranker. The texture feature extractor identifies regions in a plurality of stored images that contain homogeneous texture patterns that may vary in intensities, scales, and orientations, and extracts N-component texture feature vectors in these regions. The feature transformer maps the N-component feature vectors into a D-dimensional texture space that is invariant to texture intensity, scale, and orientation. The image ranker ranks the images according to the similarity between the texture patterns that they contain and the query texture measured in the D-dimensional invariant texture space, and the similarity between the N-component feature vectors of the texture patterns.