Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/6615
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Demirci, Muhammed Fatih | - |
dc.contributor.author | Osmanlıoğlu, Yusuf | - |
dc.contributor.author | Shokoufandeh, Ali | - |
dc.contributor.author | Dickinson, Sven | - |
dc.date.accessioned | 2021-09-11T15:42:58Z | - |
dc.date.available | 2021-09-11T15:42:58Z | - |
dc.date.issued | 2011 | en_US |
dc.identifier.issn | 1077-3142 | - |
dc.identifier.issn | 1090-235X | - |
dc.identifier.uri | https://doi.org/10.1016/j.cviu.2010.12.012 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.11851/6615 | - |
dc.description.abstract | Matching configurations of image features, represented as attributed graphs, to configurations of model features is an important component in many object recognition algorithms. Noisy segmentation of images and imprecise feature detection may lead to graphs that represent visually similar configurations that do not admit an injective matching. In previous work, we presented a framework which computed an explicit many-to-many vertex correspondence between attributed graphs of features configurations. The framework utilized a low distortion embedding function to map the nodes of the graphs into point sets in a vector space. The Earth Movers Distance (EMD) algorithm was then used to match the resulting points, with the computed flows specifying the many-to-many vertex correspondences between the input graphs. In this paper, we will present a distortion-free embedding, which represents input graphs as metric trees and then embeds them isometrically in the geometric space under the I, norm. This not only improves the representational power of graphs in the geometric space, it also reduces the complexity of the previous work using recent developments in computing EMD under l. Empirical evaluation of the algorithm on a set of recognition trials, including a comparison with previous approaches, demonstrates the effectiveness and robustness of the proposed framework. (C) 2011 Elsevier Inc. All rights reserved. | en_US |
dc.description.sponsorship | Scientific and Technological Research Council of Turkey (TUBITAK)Turkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) [109E183]; National Science FoundationNational Science Foundation (NSF) [0803670]; IIS Division and Office of Naval Research [ONR-N000140410363]; NSERC CanadaNatural Sciences and Engineering Research Council of Canada (NSERC) | en_US |
dc.description.sponsorship | The work of Fatih Demirci is supported in part by The Scientific and Technological Research Council of Turkey (TUBITAK) Grant 109E183. All Shokoufandeh gratefully acknowledges the support from the National Science Foundation Grant #0803670 under the IIS Division and Office of Naval Research Grant ONR-N000140410363. Sven Dickinson acknowledges the support of NSERC Canada. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Academic Press Inc Elsevier Science | en_US |
dc.relation.ispartof | Computer Vision And Image Understanding | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Distortion-free metric embedding | en_US |
dc.subject | Earth Mover's Distance | en_US |
dc.subject | Many-to-many matching | en_US |
dc.subject | Object recognition | en_US |
dc.title | Efficient Many-To Feature Matching Under the L(1) Norm | en_US |
dc.type | Article | en_US |
dc.department | Faculties, Faculty of Engineering, Department of Computer Engineering | en_US |
dc.department | Fakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü | tr_TR |
dc.identifier.volume | 115 | en_US |
dc.identifier.issue | 7 | en_US |
dc.identifier.startpage | 976 | en_US |
dc.identifier.endpage | 983 | en_US |
dc.authorid | 0000-0002-9997-9479 | - |
dc.identifier.wos | WOS:000291507100007 | en_US |
dc.identifier.scopus | 2-s2.0-79956151093 | en_US |
dc.institutionauthor | Demirci, Muhammed Fatih | - |
dc.identifier.doi | 10.1016/j.cviu.2010.12.012 | - |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.identifier.scopusquality | Q1 | - |
item.openairetype | Article | - |
item.languageiso639-1 | en | - |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | 02.3. Department of Computer Engineering | - |
Appears in Collections: | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
CORE Recommender
SCOPUSTM
Citations
23
checked on Dec 21, 2024
WEB OF SCIENCETM
Citations
17
checked on Nov 9, 2024
Page view(s)
134
checked on Dec 23, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.