Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Improving graph matching via density maximization
Author: Wang, C.
Wang, L.
Liu, L.
Citation: Proceedings, 2013 IEEE International Conference on Computer Vision, ICCV 2013: pp.3424-3431
Publisher: IEEE
Publisher Place: USA
Issue Date: 2013
ISBN: 9781479928392
Conference Name: IEEE International Conference on Computer Vision (14th : 2013 : Sydney, Australia)
Statement of
Chao Wang, Lei Wang, Lingqiao Liu
Abstract: Graph matching has been widely used in various applications in computer vision due to its powerful performance. However, it poses three challenges to image sparse feature matching: (1) The combinatorial nature limits the size of the possible matches, (2) It is sensitive to outliers because the objective function prefers more matches, (3) It works poorly when handling many-to-many object correspondences, due to its assumption of one single cluster for each graph. In this paper, we address these problems with a unified framework-Density Maximization. We propose a graph density local estimator (DLE) to measure the quality of matches. Density Maximization aims to maximize the DLE values both locally and globally. The local maximization of DLE finds the clusters of nodes as well as eliminates the outliers. The global maximization of DLE efficiently refines the matches by exploring a much larger matching space. Our Density Maximization is orthogonal to specific graph matching algorithms. Experimental evaluation demonstrates that it significantly boosts the true matches and enables graph matching to handle both outliers and many-to-many object correspondences.
Rights: © 2013 IEEE
DOI: 10.1109/ICCV.2013.425
Published version:
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access1.32 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.