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 effect of outliers and deformation. Experimental evaluations on synthetic graphs and real images demonstrate its higher robustness to deformation and outliers.
https://hal.inria.fr/hal-01064703 Contributor : Minsu ChoConnect in order to contact the contributor Submitted on : Wednesday, September 17, 2014 - 4:18:11 AM Last modification on : Thursday, April 28, 2022 - 4:07:37 PM Long-term archiving on: : Thursday, December 18, 2014 - 10:15:49 AM
Yumin Suh, Minsu Cho, Kyoung Mu Lee. Graph Matching via Sequential Monte Carlo. ECCV - European Conference on Computer Vision, Sep 2012, Firenze, Italy. ⟨hal-01064703⟩