PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Unified Graph Matching in Euclidean Spaces
Julian McAuley, Teo de Campos and Tiberio Caetano
In: 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 13-18 June 2010, San Francisco.

Abstract

Graph matching is a classical problem in pattern recognition with many applications, particularly when the graphs are embedded in Euclidean spaces, as is often the case for computer vision. There are several variants of the matching problem, concerned with isometries, isomorphisms, homeomorphisms, and node attributes; different approaches exist for each variant. In this paper, we show how structured estimation methods from machine learning can be used to combine such variants into a single version of graph matching. In this paradigm, the extent to which our dataset reveals isometries, isomorphisms, homeomorphisms, and other properties is automatically taken into account in the learning process so that any such specific qualification of graph matching loses meaning. We present experiments with real computer vision data showing the leverage of this unified formulation.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:6149
Deposited By:Teo de Campos
Deposited On:08 March 2010