Abstract | ||
---|---|---|
Recently, graph matching algorithms utilizing the path following strategy have exhibited state-of-the-art performances. However, the paths computed in these algorithms often contain singular points, which usually hurt the matching performance. To deal with this issue, in this paper we propose a novel path following strategy, named branching path following (BPF), which consequently improves graph matching performance. In particular, we first propose a singular point detector by solving an KKT system, and then design a branch switching method to seek for better paths at singular points. Using BPF, a new graph matching algorithm named BPF-G is developed by applying BPF to a recently proposed path following algorithm named GNCCP (Liu &Qiao 2014). For evaluation, we compare BPF-G with several recently proposed graph matching algorithms on a synthetic dataset and four public bench-mark datasets. Experimental results show that our approach achieves remarkable improvement in matching accuracy and outperforms other algorithms. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46475-6_32 | COMPUTER VISION - ECCV 2016, PT II |
Keywords | Field | DocType |
Graph matching, Path following, Numerical continuation, Singular point, Branch switching | Computer vision,Path (graph theory),Hypercube graph,Computer science,Graph factorization,Directed graph,Algorithm,Matching (graph theory),Artificial intelligence,Factor-critical graph,3-dimensional matching,Path graph | Conference |
Volume | ISSN | Citations |
9906 | 0302-9743 | 3 |
PageRank | References | Authors |
0.37 | 27 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tao Wang | 1 | 337 | 115.68 |
Haibin Ling | 2 | 4531 | 215.76 |
Congyan Lang | 3 | 353 | 39.20 |
Jun Wu | 4 | 125 | 15.66 |