Name
Abstract | ||
|---|---|---|
Graph matching is a fundamental NP-problem in computer vision and pattern recognition. In this paper, we propose a robust approximate graph matching method. The match between two graphs is formulated as an optimization problem and a novel energy function that performs random sample consensus (RANSAC) checking on the max-pooled supports is proposed. Then a belief propagation(BP) algorithm, which can assemble the spatial supports of the local neighbors in the context of the given points, is used to minimize the energy function. To achieve the one-to-(at most)-one matching constraint, we present a method for removing bad matches based on the topological structure of the graphs. Experimental results demonstrate that the proposed method outperforms other state-of-the-art graph matching methods in matching accuracy. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.neucom.2018.10.018 | Neurocomputing |
Keywords | Field | DocType |
Graph matching,Energy minimization,Random sample consensus,Max-pooled supports,Belief propagation,One-to-one match | Graph,Pattern recognition,RANSAC,Algorithm,Matching (graph theory),Sampling (statistics),Artificial intelligence,Optimization problem,Mathematics,Belief propagation | Journal |
Volume | ISSN | Citations |
325 | 0925-2312 | 1 |
PageRank | References | Authors |
0.35 | 33 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xue Lin | 1 | 1 | 1.03 |
| Dongmei Niu | 2 | 2 | 6.44 |
| Xiuyang Zhao | 3 | 73 | 13.60 |
| Bo Yang | 4 | 22 | 8.81 |
| Caiming Zhang | 5 | 446 | 88.19 |