Loading…
Dual Calibration Mechanism Based L2, p-Norm for Graph Matching
Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) f...
Saved in:
Published in: | IEEE transactions on circuits and systems for video technology 2021-06, Vol.31 (6), p.2343-2358 |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | 2358 |
container_issue | 6 |
container_start_page | 2343 |
container_title | IEEE transactions on circuits and systems for video technology |
container_volume | 31 |
creator | Yu, Yu-Feng Xu, Guoxia Huang, Ke-Kun Zhu, Hu Chen, Long Wang, Hao |
description | Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) for establishing feature points correspondence in graph matching. In specific, we embed two types of calibration modules in the graph matching, which model the correspondence relationship in point and edge respectively. The point calibration module performs unary alignment over points and the edge calibration module performs local structure alignment over edges. By performing the dual calibration, the feature points correspondence between two images with deformations and rotations variations can be obtained. To enhance the robustness of correspondence establishment, the L_{2,p} -norm is employed as the similarity metric in the proposed model, which is a flexible metric due to setting the different p values. Finally, we incorporate the dual calibration and L_{2,p} -norm based similarity metric into the graph matching model which can be optimized by an effective algorithm, and theoretically prove the convergence of the presented algorithm. Experimental results in the variety of graph matching tasks such as deformations, rotations and outliers evidence the competitive performance of the presented DCM model over the state-of-the-art approaches. |
doi_str_mv | 10.1109/TCSVT.2020.3023781 |
format | article |
fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9195466</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9195466</ieee_id><sourcerecordid>2536867055</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-e40f0af0462bcc19121b98be9fde9e5e86b9e8cd8ff6f6a7c6f002fbedfd5dbb3</originalsourceid><addsrcrecordid>eNotjb1OwzAURi0EEqXwArBYYiXl2o4de0GCAAUphYHCGtnJNXXV_OAkA29PpTKdbzj6DiGXDBaMgbld5x9f6wUHDgsBXGSaHZEZk1InnIM83m-QLNGcyVNyNgxbAJbqNJuRu8fJ7mhud8FFO4aupSusNrYNQ0Mf7IA1LfgN7ZO3LjbUd5Euo-03dGXHahPa73Ny4u1uwIt_zsnn89M6f0mK9-Vrfl8kgYMYE0zBg_WQKu6qihnGmTPaofE1GpSolTOoq1p7r7yyWaU8APcOa1_L2jkxJ9eH3z52PxMOY7ntptjukyWXQmmVgZR76-pgBUQs-xgaG39Lw4xMlRJ_tupUNw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2536867055</pqid></control><display><type>article</type><title>Dual Calibration Mechanism Based L2, p-Norm for Graph Matching</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Yu, Yu-Feng ; Xu, Guoxia ; Huang, Ke-Kun ; Zhu, Hu ; Chen, Long ; Wang, Hao</creator><creatorcontrib>Yu, Yu-Feng ; Xu, Guoxia ; Huang, Ke-Kun ; Zhu, Hu ; Chen, Long ; Wang, Hao</creatorcontrib><description><![CDATA[Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) for establishing feature points correspondence in graph matching. In specific, we embed two types of calibration modules in the graph matching, which model the correspondence relationship in point and edge respectively. The point calibration module performs unary alignment over points and the edge calibration module performs local structure alignment over edges. By performing the dual calibration, the feature points correspondence between two images with deformations and rotations variations can be obtained. To enhance the robustness of correspondence establishment, the <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm is employed as the similarity metric in the proposed model, which is a flexible metric due to setting the different <inline-formula> <tex-math notation="LaTeX">p </tex-math></inline-formula> values. Finally, we incorporate the dual calibration and <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm based similarity metric into the graph matching model which can be optimized by an effective algorithm, and theoretically prove the convergence of the presented algorithm. Experimental results in the variety of graph matching tasks such as deformations, rotations and outliers evidence the competitive performance of the presented DCM model over the state-of-the-art approaches.]]></description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2020.3023781</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Alignment ; Calibration ; Calibration mechanism ; Correspondence ; Graph matching ; Image edge detection ; Image enhancement ; Linear programming ; Model matching ; Modules ; Robustness ; Similarity ; similarity metric ; Strain ; Task analysis</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2021-06, Vol.31 (6), p.2343-2358</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0001-9301-5989 ; 0000-0002-5528-8721 ; 0000-0002-0036-8820 ; 0000-0002-8207-0496 ; 0000-0003-0184-5446</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9195466$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,786,790,27957,27958,55147</link.rule.ids></links><search><creatorcontrib>Yu, Yu-Feng</creatorcontrib><creatorcontrib>Xu, Guoxia</creatorcontrib><creatorcontrib>Huang, Ke-Kun</creatorcontrib><creatorcontrib>Zhu, Hu</creatorcontrib><creatorcontrib>Chen, Long</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><title>Dual Calibration Mechanism Based L2, p-Norm for Graph Matching</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description><![CDATA[Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) for establishing feature points correspondence in graph matching. In specific, we embed two types of calibration modules in the graph matching, which model the correspondence relationship in point and edge respectively. The point calibration module performs unary alignment over points and the edge calibration module performs local structure alignment over edges. By performing the dual calibration, the feature points correspondence between two images with deformations and rotations variations can be obtained. To enhance the robustness of correspondence establishment, the <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm is employed as the similarity metric in the proposed model, which is a flexible metric due to setting the different <inline-formula> <tex-math notation="LaTeX">p </tex-math></inline-formula> values. Finally, we incorporate the dual calibration and <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm based similarity metric into the graph matching model which can be optimized by an effective algorithm, and theoretically prove the convergence of the presented algorithm. Experimental results in the variety of graph matching tasks such as deformations, rotations and outliers evidence the competitive performance of the presented DCM model over the state-of-the-art approaches.]]></description><subject>Algorithms</subject><subject>Alignment</subject><subject>Calibration</subject><subject>Calibration mechanism</subject><subject>Correspondence</subject><subject>Graph matching</subject><subject>Image edge detection</subject><subject>Image enhancement</subject><subject>Linear programming</subject><subject>Model matching</subject><subject>Modules</subject><subject>Robustness</subject><subject>Similarity</subject><subject>similarity metric</subject><subject>Strain</subject><subject>Task analysis</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNotjb1OwzAURi0EEqXwArBYYiXl2o4de0GCAAUphYHCGtnJNXXV_OAkA29PpTKdbzj6DiGXDBaMgbld5x9f6wUHDgsBXGSaHZEZk1InnIM83m-QLNGcyVNyNgxbAJbqNJuRu8fJ7mhud8FFO4aupSusNrYNQ0Mf7IA1LfgN7ZO3LjbUd5Euo-03dGXHahPa73Ny4u1uwIt_zsnn89M6f0mK9-Vrfl8kgYMYE0zBg_WQKu6qihnGmTPaofE1GpSolTOoq1p7r7yyWaU8APcOa1_L2jkxJ9eH3z52PxMOY7ntptjukyWXQmmVgZR76-pgBUQs-xgaG39Lw4xMlRJ_tupUNw</recordid><startdate>20210601</startdate><enddate>20210601</enddate><creator>Yu, Yu-Feng</creator><creator>Xu, Guoxia</creator><creator>Huang, Ke-Kun</creator><creator>Zhu, Hu</creator><creator>Chen, Long</creator><creator>Wang, Hao</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-9301-5989</orcidid><orcidid>https://orcid.org/0000-0002-5528-8721</orcidid><orcidid>https://orcid.org/0000-0002-0036-8820</orcidid><orcidid>https://orcid.org/0000-0002-8207-0496</orcidid><orcidid>https://orcid.org/0000-0003-0184-5446</orcidid></search><sort><creationdate>20210601</creationdate><title>Dual Calibration Mechanism Based L2, p-Norm for Graph Matching</title><author>Yu, Yu-Feng ; Xu, Guoxia ; Huang, Ke-Kun ; Zhu, Hu ; Chen, Long ; Wang, Hao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-e40f0af0462bcc19121b98be9fde9e5e86b9e8cd8ff6f6a7c6f002fbedfd5dbb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Alignment</topic><topic>Calibration</topic><topic>Calibration mechanism</topic><topic>Correspondence</topic><topic>Graph matching</topic><topic>Image edge detection</topic><topic>Image enhancement</topic><topic>Linear programming</topic><topic>Model matching</topic><topic>Modules</topic><topic>Robustness</topic><topic>Similarity</topic><topic>similarity metric</topic><topic>Strain</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yu, Yu-Feng</creatorcontrib><creatorcontrib>Xu, Guoxia</creatorcontrib><creatorcontrib>Huang, Ke-Kun</creatorcontrib><creatorcontrib>Zhu, Hu</creatorcontrib><creatorcontrib>Chen, Long</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Xplore</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on circuits and systems for video technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Yu-Feng</au><au>Xu, Guoxia</au><au>Huang, Ke-Kun</au><au>Zhu, Hu</au><au>Chen, Long</au><au>Wang, Hao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dual Calibration Mechanism Based L2, p-Norm for Graph Matching</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2021-06-01</date><risdate>2021</risdate><volume>31</volume><issue>6</issue><spage>2343</spage><epage>2358</epage><pages>2343-2358</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract><![CDATA[Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal with this problem, in this work, we propose a dual calibration mechanism (DCM) for establishing feature points correspondence in graph matching. In specific, we embed two types of calibration modules in the graph matching, which model the correspondence relationship in point and edge respectively. The point calibration module performs unary alignment over points and the edge calibration module performs local structure alignment over edges. By performing the dual calibration, the feature points correspondence between two images with deformations and rotations variations can be obtained. To enhance the robustness of correspondence establishment, the <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm is employed as the similarity metric in the proposed model, which is a flexible metric due to setting the different <inline-formula> <tex-math notation="LaTeX">p </tex-math></inline-formula> values. Finally, we incorporate the dual calibration and <inline-formula> <tex-math notation="LaTeX">L_{2,p} </tex-math></inline-formula>-norm based similarity metric into the graph matching model which can be optimized by an effective algorithm, and theoretically prove the convergence of the presented algorithm. Experimental results in the variety of graph matching tasks such as deformations, rotations and outliers evidence the competitive performance of the presented DCM model over the state-of-the-art approaches.]]></abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSVT.2020.3023781</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0001-9301-5989</orcidid><orcidid>https://orcid.org/0000-0002-5528-8721</orcidid><orcidid>https://orcid.org/0000-0002-0036-8820</orcidid><orcidid>https://orcid.org/0000-0002-8207-0496</orcidid><orcidid>https://orcid.org/0000-0003-0184-5446</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1051-8215 |
ispartof | IEEE transactions on circuits and systems for video technology, 2021-06, Vol.31 (6), p.2343-2358 |
issn | 1051-8215 1558-2205 |
language | eng |
recordid | cdi_ieee_primary_9195466 |
source | IEEE Electronic Library (IEL) Journals |
subjects | Algorithms Alignment Calibration Calibration mechanism Correspondence Graph matching Image edge detection Image enhancement Linear programming Model matching Modules Robustness Similarity similarity metric Strain Task analysis |
title | Dual Calibration Mechanism Based L2, p-Norm for Graph Matching |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-23T05%3A30%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Dual%20Calibration%20Mechanism%20Based%20L2,%20p-Norm%20for%20Graph%20Matching&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Yu,%20Yu-Feng&rft.date=2021-06-01&rft.volume=31&rft.issue=6&rft.spage=2343&rft.epage=2358&rft.pages=2343-2358&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2020.3023781&rft_dat=%3Cproquest_ieee_%3E2536867055%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-e40f0af0462bcc19121b98be9fde9e5e86b9e8cd8ff6f6a7c6f002fbedfd5dbb3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2536867055&rft_id=info:pmid/&rft_ieee_id=9195466&rfr_iscdi=true |