Graphical models and point pattern matching
Autor(a) principal: | |
---|---|
Data de Publicação: | 2006 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/27603 |
Resumo: | This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case. First, we model point pattern matching as a weighted graph matching problem, where weights correspond to Euclidean distances between nodes. We then formulate graph matching as a problem of finding a maximum probability configuration in a graphical model By using graph rigidity arguments, we prove that a sparse graphical model yields equivalent results to the fully connected model in the noiseless case. This allows us to obtain an algorithm that runs in polynomial time and is provably optimal for exact matching between noiseless point sets. For inexact matching, we can still apply the same algorithm to find approximately optimal solutions. Experimental results obtained by our approach show improvements in accuracy over current methods, particularly when matching patterns of different sizes. |
id |
UFRGS-2_6e3929c1e70a22869c6a3639d0443a1b |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/27603 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Caetano, Tiberio SilvaCaelli, TerrySchuurmans, DaleBarone, Dante Augusto Couto2011-01-29T06:00:36Z20060162-8828http://hdl.handle.net/10183/27603000585735This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case. First, we model point pattern matching as a weighted graph matching problem, where weights correspond to Euclidean distances between nodes. We then formulate graph matching as a problem of finding a maximum probability configuration in a graphical model By using graph rigidity arguments, we prove that a sparse graphical model yields equivalent results to the fully connected model in the noiseless case. This allows us to obtain an algorithm that runs in polynomial time and is provably optimal for exact matching between noiseless point sets. For inexact matching, we can still apply the same algorithm to find approximately optimal solutions. Experimental results obtained by our approach show improvements in accuracy over current methods, particularly when matching patterns of different sizes.application/pdfengIEEE transactions on pattern analysis and machine intelligence. New York. Vol. 28, n. 10 (Oct. 2006), p. 1646-1663Computação gráficaReconhecimento : PadroesPoint pattern matchingGraph matchingGraphical modelsMarkov random fieldsJunction tree algorithmGraphical models and point pattern matchingEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL000585735.pdf000585735.pdfTexto completo (inglês)application/pdf2454125http://www.lume.ufrgs.br/bitstream/10183/27603/1/000585735.pdff48a2a0f6b170d907e60d9554b9b48f8MD51TEXT000585735.pdf.txt000585735.pdf.txtExtracted Texttext/plain92535http://www.lume.ufrgs.br/bitstream/10183/27603/2/000585735.pdf.txtee29bcb15ef267ec55ce1e70e92512dcMD52THUMBNAIL000585735.pdf.jpg000585735.pdf.jpgGenerated Thumbnailimage/jpeg2182http://www.lume.ufrgs.br/bitstream/10183/27603/3/000585735.pdf.jpg8bb329e286884a9e9aa2d83c1cb986d2MD5310183/276032021-06-13 04:33:59.334477oai:www.lume.ufrgs.br:10183/27603Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-06-13T07:33:59Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Graphical models and point pattern matching |
title |
Graphical models and point pattern matching |
spellingShingle |
Graphical models and point pattern matching Caetano, Tiberio Silva Computação gráfica Reconhecimento : Padroes Point pattern matching Graph matching Graphical models Markov random fields Junction tree algorithm |
title_short |
Graphical models and point pattern matching |
title_full |
Graphical models and point pattern matching |
title_fullStr |
Graphical models and point pattern matching |
title_full_unstemmed |
Graphical models and point pattern matching |
title_sort |
Graphical models and point pattern matching |
author |
Caetano, Tiberio Silva |
author_facet |
Caetano, Tiberio Silva Caelli, Terry Schuurmans, Dale Barone, Dante Augusto Couto |
author_role |
author |
author2 |
Caelli, Terry Schuurmans, Dale Barone, Dante Augusto Couto |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Caetano, Tiberio Silva Caelli, Terry Schuurmans, Dale Barone, Dante Augusto Couto |
dc.subject.por.fl_str_mv |
Computação gráfica Reconhecimento : Padroes |
topic |
Computação gráfica Reconhecimento : Padroes Point pattern matching Graph matching Graphical models Markov random fields Junction tree algorithm |
dc.subject.eng.fl_str_mv |
Point pattern matching Graph matching Graphical models Markov random fields Junction tree algorithm |
description |
This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case. First, we model point pattern matching as a weighted graph matching problem, where weights correspond to Euclidean distances between nodes. We then formulate graph matching as a problem of finding a maximum probability configuration in a graphical model By using graph rigidity arguments, we prove that a sparse graphical model yields equivalent results to the fully connected model in the noiseless case. This allows us to obtain an algorithm that runs in polynomial time and is provably optimal for exact matching between noiseless point sets. For inexact matching, we can still apply the same algorithm to find approximately optimal solutions. Experimental results obtained by our approach show improvements in accuracy over current methods, particularly when matching patterns of different sizes. |
publishDate |
2006 |
dc.date.issued.fl_str_mv |
2006 |
dc.date.accessioned.fl_str_mv |
2011-01-29T06:00:36Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/27603 |
dc.identifier.issn.pt_BR.fl_str_mv |
0162-8828 |
dc.identifier.nrb.pt_BR.fl_str_mv |
000585735 |
identifier_str_mv |
0162-8828 000585735 |
url |
http://hdl.handle.net/10183/27603 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
IEEE transactions on pattern analysis and machine intelligence. New York. Vol. 28, n. 10 (Oct. 2006), p. 1646-1663 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/27603/1/000585735.pdf http://www.lume.ufrgs.br/bitstream/10183/27603/2/000585735.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/27603/3/000585735.pdf.jpg |
bitstream.checksum.fl_str_mv |
f48a2a0f6b170d907e60d9554b9b48f8 ee29bcb15ef267ec55ce1e70e92512dc 8bb329e286884a9e9aa2d83c1cb986d2 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801224724615790592 |