.png){kind=icon}
Return
Subgraph learning for graph matching
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2018.07.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph matching is a powerful tool for computer vision, distance measure and machine learning. However, many factors influences the accuracy of matching. The outliers is a key problem in the process of matching. In this paper, a novel approach is proposed to handle graph matching problem based on Markov Chain Monte Carlo framework. By constructing a target distribution, the proposed can perform a process of sampling to maximize the graph matching objective. In this process, our method can effectively save matching pairwise under one-to-one matching constraints and also avoid the effect of outliers and deformation. The corresponding experiments on synthetic graphs, real images and view-based 3D model retrieval demonstrate the superiority of the proposed method. (C) 2018 Elsevier B.V. All rights reserved.
Keywords:
Graph matching
Markov Chain Monte Carlo
Image matching
Object retrieval
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
7.9K
Citations:
1.6W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSave
View more