Attributed hypergraph matching on a Riemannian manifold

J. M. Wang, Sei-Wang Chen, C. S. Fuh

研究成果: 雜誌貢獻文章

2 引文 (Scopus)

摘要

If we consider a matching that preserves high-order relationships among points in the same set, we can int-roduce a hypergraph-matching technique to search for correspondence according to high-order feature values. While graph matching has been widely studied, there is limited research available regarding hypergraph matching. In this paper, we formulate hypergraph matching in terms of tensors. Then, we reduce the hypergraph matching to a bipartite matching problem that can be solved in polynomial time. We then extend this hypergraph matching to attributed hypergraph matching using a combination of different attributes with different orders. We perform analyses that demonstrate that this method is robust when handling noisy or missing data and can achieve inexact graph matching. To the best of our knowledge, while attributed graph-matching and hypergraph-matching have been heavily researched, methods for attributed hypergraph matching have not been proposed before.

原文英語
頁(從 - 到)823-844
頁數22
期刊Machine Vision and Applications
25
發行號4
DOIs
出版狀態已發佈 - 2014 一月 1

指紋

Tensors
Polynomials

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

引用此文

Attributed hypergraph matching on a Riemannian manifold. / Wang, J. M.; Chen, Sei-Wang; Fuh, C. S.

於: Machine Vision and Applications, 卷 25, 編號 4, 01.01.2014, p. 823-844.

研究成果: 雜誌貢獻文章

Wang, J. M. ; Chen, Sei-Wang ; Fuh, C. S. / Attributed hypergraph matching on a Riemannian manifold. 於: Machine Vision and Applications. 2014 ; 卷 25, 編號 4. 頁 823-844.
@article{3b67046eb0df4df7ba56c686dff9db04,
title = "Attributed hypergraph matching on a Riemannian manifold",
abstract = "If we consider a matching that preserves high-order relationships among points in the same set, we can int-roduce a hypergraph-matching technique to search for correspondence according to high-order feature values. While graph matching has been widely studied, there is limited research available regarding hypergraph matching. In this paper, we formulate hypergraph matching in terms of tensors. Then, we reduce the hypergraph matching to a bipartite matching problem that can be solved in polynomial time. We then extend this hypergraph matching to attributed hypergraph matching using a combination of different attributes with different orders. We perform analyses that demonstrate that this method is robust when handling noisy or missing data and can achieve inexact graph matching. To the best of our knowledge, while attributed graph-matching and hypergraph-matching have been heavily researched, methods for attributed hypergraph matching have not been proposed before.",
keywords = "Attributed hypergraph matching, Graph matching, Hilbert space, Inexact graph matching, Riemannian manifold",
author = "Wang, {J. M.} and Sei-Wang Chen and Fuh, {C. S.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s00138-014-0598-1",
language = "English",
volume = "25",
pages = "823--844",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "4",

}

TY - JOUR

T1 - Attributed hypergraph matching on a Riemannian manifold

AU - Wang, J. M.

AU - Chen, Sei-Wang

AU - Fuh, C. S.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - If we consider a matching that preserves high-order relationships among points in the same set, we can int-roduce a hypergraph-matching technique to search for correspondence according to high-order feature values. While graph matching has been widely studied, there is limited research available regarding hypergraph matching. In this paper, we formulate hypergraph matching in terms of tensors. Then, we reduce the hypergraph matching to a bipartite matching problem that can be solved in polynomial time. We then extend this hypergraph matching to attributed hypergraph matching using a combination of different attributes with different orders. We perform analyses that demonstrate that this method is robust when handling noisy or missing data and can achieve inexact graph matching. To the best of our knowledge, while attributed graph-matching and hypergraph-matching have been heavily researched, methods for attributed hypergraph matching have not been proposed before.

AB - If we consider a matching that preserves high-order relationships among points in the same set, we can int-roduce a hypergraph-matching technique to search for correspondence according to high-order feature values. While graph matching has been widely studied, there is limited research available regarding hypergraph matching. In this paper, we formulate hypergraph matching in terms of tensors. Then, we reduce the hypergraph matching to a bipartite matching problem that can be solved in polynomial time. We then extend this hypergraph matching to attributed hypergraph matching using a combination of different attributes with different orders. We perform analyses that demonstrate that this method is robust when handling noisy or missing data and can achieve inexact graph matching. To the best of our knowledge, while attributed graph-matching and hypergraph-matching have been heavily researched, methods for attributed hypergraph matching have not been proposed before.

KW - Attributed hypergraph matching

KW - Graph matching

KW - Hilbert space

KW - Inexact graph matching

KW - Riemannian manifold

UR - http://www.scopus.com/inward/record.url?scp=84899912766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899912766&partnerID=8YFLogxK

U2 - 10.1007/s00138-014-0598-1

DO - 10.1007/s00138-014-0598-1

M3 - Article

AN - SCOPUS:84899912766

VL - 25

SP - 823

EP - 844

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 4

ER -