Showing papers by "Stan Z. Li published in 1990"

Invariant surface segmentation through energy minimization with discontinuities

Abstract: The computational problems in segmenting range data into surface patches based on the invariant surface properties, i.e., mean curvature H and Gaussian curvature K, are investigated. The goal is to obtain reliable HK surface maps. Two commonly encountered problems are: firstly the noise effect in computing derivative estimates, and secondly the smoothing across discontinuities. Here, the segmentation is formulated as finding minimization solutions of energy functionals involving discontinuities. A two-stage approach to the goal is presented: stage (1) from a range image to curvature images and stage (2) from the curvature images to the HK maps. In both stages, solutions are found through minimizing energy functionals that measure the degree of bias of a solution from two constraints: the closeness of the solution to the data, and the smoothness of the solution controlled by predetermined discontinuities. Propagation across discontinuities is prevented during minimization, which preserves the original surface shapes. Experimental results are given for a variety of test images.

Reconstruction without discontinuities

Abstract: Discontinuities have been important in visual reconstruction to avoid oversmoothing. The article raises the question as to whether location of discontinuities is necessary in this process. The author proposes a class of adaptive regularizers (ARs) for reconstruction in the framework of regularization, in an attempt to solve the conflict between 'oversmoothing across discontinuities' and 'finding discontinuities'. The proposal differs from existing methods in the way it controls continuity, in which true discontinuities are considered in the mathematical sense only. A simple analog neuron-like circuit for hardware implementation is suggested. Experimental results are presented. >