Faster alpha-expansion via dynamic programming and image partitioning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://hdl.handle.net/11449/209250 |
Resumo: | Image segmentation is the task of assigning a label to each image pixel. When the number of labels is greater than two (multi-label) the segmentation can be modelled as a multi-cut problem in graphs. In the general case, finding the minimum cut in a graph is an NP-hard problem, in which improving the results concerning time and quality is a major challenge. This paper addresses the multi-label problem applied in interactive image segmentation. The proposed approach makes use of dynamic programming to initialize an alpha-expansion, thus reducing its runtime, while keeping the Dice-score measure in an interactive segmentation task. Over BSDS data set, the proposed algorithm was approximately 51.2% faster than its standard counterpart, 36.2% faster than Fast Primal-Dual (FastPD) and 10.5 times faster than quadratic pseudo-boolean optimization (QBPO) optimizers, while preserving the same segmentation quality. |
id |
UNSP_3ffe8bf1b63cceba41c49ff243e3c20b |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/209250 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Faster alpha-expansion via dynamic programming and image partitioningalpha-expansiondynamic programmingmulti-labelimage segmentationImage segmentation is the task of assigning a label to each image pixel. When the number of labels is greater than two (multi-label) the segmentation can be modelled as a multi-cut problem in graphs. In the general case, finding the minimum cut in a graph is an NP-hard problem, in which improving the results concerning time and quality is a major challenge. This paper addresses the multi-label problem applied in interactive image segmentation. The proposed approach makes use of dynamic programming to initialize an alpha-expansion, thus reducing its runtime, while keeping the Dice-score measure in an interactive segmentation task. Over BSDS data set, the proposed algorithm was approximately 51.2% faster than its standard counterpart, 36.2% faster than Fast Primal-Dual (FastPD) and 10.5 times faster than quadratic pseudo-boolean optimization (QBPO) optimizers, while preserving the same segmentation quality.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Univ Fed Bahia, Intelligent Vis Res Lab, Salvador, BA, BrazilVORTEX CoLab, Porto, PortugalSao Paulo State Univ, Bauru, SP, BrazilSao Paulo State Univ, Bauru, SP, BrazilCNPq: 307550/2018-4CNPq: 307066/2017-7FAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2017/25908-6IeeeUniversidade Federal da Bahia (UFBA)VORTEX CoLabUniversidade Estadual Paulista (Unesp)Fontinele, JeffersonMendonca, MarceloRuiz, MarcoPapa, Joao [UNESP]Oliveira, LucianoIEEE2021-06-25T11:54:12Z2021-06-25T11:54:12Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject82020 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2020.2161-4393http://hdl.handle.net/11449/209250WOS:000626021403067Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2020 International Joint Conference On Neural Networks (ijcnn)info:eu-repo/semantics/openAccess2021-10-23T19:23:40Zoai:repositorio.unesp.br:11449/209250Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:00:46.629756Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Faster alpha-expansion via dynamic programming and image partitioning |
title |
Faster alpha-expansion via dynamic programming and image partitioning |
spellingShingle |
Faster alpha-expansion via dynamic programming and image partitioning Fontinele, Jefferson alpha-expansion dynamic programming multi-label image segmentation |
title_short |
Faster alpha-expansion via dynamic programming and image partitioning |
title_full |
Faster alpha-expansion via dynamic programming and image partitioning |
title_fullStr |
Faster alpha-expansion via dynamic programming and image partitioning |
title_full_unstemmed |
Faster alpha-expansion via dynamic programming and image partitioning |
title_sort |
Faster alpha-expansion via dynamic programming and image partitioning |
author |
Fontinele, Jefferson |
author_facet |
Fontinele, Jefferson Mendonca, Marcelo Ruiz, Marco Papa, Joao [UNESP] Oliveira, Luciano IEEE |
author_role |
author |
author2 |
Mendonca, Marcelo Ruiz, Marco Papa, Joao [UNESP] Oliveira, Luciano IEEE |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal da Bahia (UFBA) VORTEX CoLab Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Fontinele, Jefferson Mendonca, Marcelo Ruiz, Marco Papa, Joao [UNESP] Oliveira, Luciano IEEE |
dc.subject.por.fl_str_mv |
alpha-expansion dynamic programming multi-label image segmentation |
topic |
alpha-expansion dynamic programming multi-label image segmentation |
description |
Image segmentation is the task of assigning a label to each image pixel. When the number of labels is greater than two (multi-label) the segmentation can be modelled as a multi-cut problem in graphs. In the general case, finding the minimum cut in a graph is an NP-hard problem, in which improving the results concerning time and quality is a major challenge. This paper addresses the multi-label problem applied in interactive image segmentation. The proposed approach makes use of dynamic programming to initialize an alpha-expansion, thus reducing its runtime, while keeping the Dice-score measure in an interactive segmentation task. Over BSDS data set, the proposed algorithm was approximately 51.2% faster than its standard counterpart, 36.2% faster than Fast Primal-Dual (FastPD) and 10.5 times faster than quadratic pseudo-boolean optimization (QBPO) optimizers, while preserving the same segmentation quality. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2021-06-25T11:54:12Z 2021-06-25T11:54:12Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
2020 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2020. 2161-4393 http://hdl.handle.net/11449/209250 WOS:000626021403067 |
identifier_str_mv |
2020 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2020. 2161-4393 WOS:000626021403067 |
url |
http://hdl.handle.net/11449/209250 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2020 International Joint Conference On Neural Networks (ijcnn) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
8 |
dc.publisher.none.fl_str_mv |
Ieee |
publisher.none.fl_str_mv |
Ieee |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128884361658368 |