NEW ALGORITHMS FOR 2D AND 3D POINT MATCHING - POSE ESTIMATION AND CORRESPONDENCE

A fundamental open problem in computer vision-determining pose and cor respondence between two sets of points in space-is solved with a novel , fast, robust and easily implementable algorithm. The technique works on noisy 2D or 3D point sets that may be of unequal sizes and may dif fer by non-rigid transformations. Using a combination of optimization techniques such as deterministic annealing and the softassign, which h ave recently emerged out of the recurrent neural network/statistical p hysics framework, analog objective functions describing the problems a re minimized. Over thirty thousand experiments, on randomly generated points sets with varying amounts of noise and missing and spurious poi nts, and on hand-written character sets demonstrate the robustness of the algorithm. (C) 1998 Pattern Recognition Society. Published by Else vier Science Ltd. All rights reserved.