Search

A coarse-to-fine registration algorithm uses the orthogonal wavelet pyramid decomposition, and compensates for the absence of translation invariance in the representation. Boundary curvature maps registration reveal the suitability of Laplacian pyramids. Matching applications are performed using filters that produce coarse representations which facilitate comparison with library prototypes.

Curvature sampling of arbitrary, fully described 3-D objects (e.g., tomographic medical images) is difficult because of surface patch parameterization problems. Five practical solutions are presented and characterized--the Sander-Zucker approach, two new methods based on direct surface mapping, a piece-wise linear manifold technique, and a turtle geometry method. One of these new methods, called the cross patch (CP) method, is shown to be very fast, robust in the presence of noise, and is always based on a proper surface parameterization, provided the perturbations of the surface over the patch neighborhood are isotropically distributed.