Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/7003
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shokoufandeh, A. | - |
dc.contributor.author | Keselman, Y. | - |
dc.contributor.author | Demirci, M. F. | - |
dc.contributor.author | Macrini, D. | - |
dc.contributor.author | Dickinson, S. | - |
dc.date.accessioned | 2021-09-11T15:44:49Z | - |
dc.date.available | 2021-09-11T15:44:49Z | - |
dc.date.issued | 2012 | en_US |
dc.identifier.issn | 1751-9632 | - |
dc.identifier.issn | 1751-9640 | - |
dc.identifier.uri | https://doi.org/10.1049/iet-cvi.2012.0030 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.11851/7003 | - |
dc.description.abstract | The mainstream object categorisation community relies heavily on object representations consisting of local image features, due to their ease of recovery and their attractive invariance properties. Object categorisation is therefore formulated as finding, that is, 'detecting', a one-to-one correspondence between image and model features. This assumption breaks down for categories in which two exemplars may not share a single local image feature. Even when objects are represented as more abstract image features, a collection of features at one scale (in one image) may correspond to a single feature at a coarser scale (in the second image). Effective object categorisation therefore requires the ability to match features many-to-many. In this paper, we review our progress on three independent object categorisation problems, each formulated as a graph matching problem and each solving the many-to-many graph matching problem in a different way. First, we explore the problem of learning a shape class prototype from a set of class exemplars which may not share a single local image feature. Next, we explore the problem of matching two graphs in which correspondence exists only at higher levels of abstraction, and describe a low-dimensional, spectral encoding of graph structure that captures the abstract shape of a graph. Finally, we embed graphs into geometric spaces, reducing the many-to-many graph-matching problem to a weighted point matching problem, for which efficient many-to-many matching algorithms exist. | en_US |
dc.description.sponsorship | NSERCNatural Sciences and Engineering Research Council of Canada (NSERC); IRIS; NSFNational Science Foundation (NSF); ONROffice of Naval Research; DARPAUnited States Department of DefenseDefense Advanced Research Projects Agency (DARPA); PREA | en_US |
dc.description.sponsorship | The authors gratefully acknowledge the support of NSERC, IRIS, NSF, ONR, DARPA, and PREA. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Wiley | en_US |
dc.relation.ispartof | Iet Computer Vision | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | [No Keywords] | en_US |
dc.title | Many-To Feature Matching in Object Recognition: a Review of Three Approaches | en_US |
dc.type | Review | 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 | 6 | en_US |
dc.identifier.issue | 6 | en_US |
dc.identifier.startpage | 500 | en_US |
dc.identifier.endpage | 513 | en_US |
dc.identifier.wos | WOS:000318228200002 | en_US |
dc.identifier.scopus | 2-s2.0-84879735073 | en_US |
dc.institutionauthor | Demirci, Muhammed Fatih | - |
dc.identifier.doi | 10.1049/iet-cvi.2012.0030 | - |
dc.relation.publicationcategory | Diğer | en_US |
dc.identifier.scopusquality | Q3 | - |
item.openairetype | Review | - |
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
22
checked on Dec 21, 2024
WEB OF SCIENCETM
Citations
18
checked on Oct 5, 2024
Page view(s)
62
checked on Dec 16, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.