Approximating the problem, not the solution: An alternative view of point set matching

PATTERN RECOGNITION

卷:39

Article; Proceedings Paper

Caetano, TS ; Caelli, T

关键词: graphical models;    point pattern matching;    graph matching;    Markov random fields;   

DOI  :  10.1016/j.patcog.2005.10.005

来源: Elsevier

【 摘 要 】

This work discusses the issue of approximation in point set matching. In general, one may have two classes of approximations when tackling a matching problem: (1) an algorithmic approximation which consists in using suboptimal procedures to infer the assignment, and (2), a representational approximation which involves a simplified and suboptimal model for the original data. Matching techniques have typically relied on the first approach by retaining the complete model and using suboptimal techniques to solve it. In this paper, we show how a technique based on using exact inference in simple Graphical Models, an instance of the second class, can significantly outperform instances of techniques from the first class. We experimentally compare this method with well-known Spectral and Relaxation methods, which are exemplars of the first class. We have performed experiments with synthetic and real-world data sets which reveal significant performance improvement in a wide operating range. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

【 授权许可】

Free