Volume Data Approximation Using Wavelet Transforms

Abstract

A method is developed to obtain a unique shape description of an object by using wavelet transforms. Volume data of the object can be decomposed into a set of local primitives by applying 3D wavelet transforms, and further a “multiresolution expression” of the object can then be obtained. By using smoothly vanishing basis functions, the shape is approximated with a relatively small number of primitives without causing discontinuity on the surface. In addition, the resolution of the approximation can be varied point by point using the local property of the wavelets and “multiresolution expression”. The method is applied to real volume data, such as facial range data and MR images of a human head, and typical results are explained.