Name
Abstract | ||
|---|---|---|
The graph matching problem is a hot topic in machine vision. Although a myriad of matching algorithms have been proposed during decades of investigation, it is still a challenging issue because of the combinatorial nature. As one of the outstanding graph matching algorithms, the follows the algorithm. The main drawback of this approach lies that there may exist which violate the smoothness of the solution path and thus harm the accuracy of matching. Addressing this problem, we develop a novel algorithm to bypass this pitfall to improve the matching accuracy. We design an effective method of singular point discovering by checking the smoothness of the path and subsequently explore multiple smooth curves at detected points for better matching results. For evaluation, we make comparisons between our approach and several outstanding matching algorithms on three popular benchmarks, and the results reveal the advantage of our approach. |
Year | DOI | Venue |
|---|---|---|
2017 | https://doi.org/10.1007/s00138-017-0847-1 | Mach. Vis. Appl. |
Keywords | Field | DocType |
Graph matching,GNCCP,Path following,Singular point,Multiple smooth curves | Drawback,Machine vision,Computer science,Artificial intelligence,Smoothness,Singular point of a curve,Mathematical optimization,Optimal matching,Pattern recognition,Effective method,Algorithm,Matching (graph theory),3-dimensional matching | Journal |
Volume | Issue | ISSN |
28 | 7 | 0932-8092 |
Citations | PageRank | References |
1 | 0.37 | 26 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ran Chen | 1 | 4 | 2.61 |
| Congyan Lang | 2 | 353 | 39.20 |
| Tao Wang | 3 | 337 | 115.68 |