Abstract

A fundamental open problem in computer vision—determining pose and correspondence 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 differ by non-rigid transformations. Using a combination of optimization techniques such as deterministic annealing and the softassign, which have recently emerged out of the recurrent neural network/statistical physics framework, analog objective functions describing the problems are minimized. Over thirty thousand experiments, on randomly generated points sets with varying amounts of noise and missing and spurious points, and on hand-written character sets demonstrate the robustness of the algorithm.

Keywords

Spurious relationshipAlgorithmRobustness (evolution)Computer sciencePoint set registrationSimulated annealingArtificial neural networkPoint (geometry)Artificial intelligenceMatching (statistics)MathematicsMachine learning

Affiliated Institutions

Related Publications

Publication Info

Year
1998
Type
article
Volume
31
Issue
8
Pages
1019-1031
Citations
571
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

571
OpenAlex

Cite This

Steven Gold, Anand Rangarajan, Chien-Ping Lu et al. (1998). New algorithms for 2D and 3D point matching. Pattern Recognition , 31 (8) , 1019-1031. https://doi.org/10.1016/s0031-3203(98)80010-1

Identifiers

DOI
10.1016/s0031-3203(98)80010-1