Graph Matching via Sequential Monte Carlo

Authors

Abstract

Graph matching is a powerful tool for computer vision and machine learning. In this paper, a novel approach to graph matching is developed based on the sequential Monte Carlo framework. By constructing a sequence of intermediate target distributions, the proposed algorithm sequentially performs a sampling and importance resampling to maximize the graph matching objective. Through the sequential sampling procedure, the algorithm effectively collects potential matches under one-to-one matching constraints to avoid the adverse efect of outliers and deformation. Experimental evaluations on synthetic graphs and real images demonstrate its higher robustness to deformation and outliers.

Paper

ECCV 2012 paper

Presentation

ECCV 2012 poster (pdf, 4.75 MB)
video (wmv, 2.81 MB)

Code

code (zip, 65.0 KB) - updated Feb 2013

Dataset

png images (zip, 10.2 MB)

Citation

Yumin Suh, Minsu Cho and Kyoung Mu Lee, "Graph Matching via Sequential Monte Carlo", Proc. of European Conference on Computer Vision (ECCV), 2012. Bibtex