Faster α-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://dx.doi.org/10.1109/IJCNN48605.2020.9207032 http://hdl.handle.net/11449/221592 |
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 α-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_a01f7a4caafec92644c5bd2673d085cc |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/221592 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Faster α-expansion via dynamic programming and image partitioningdynamic programmingimage segmentationmulti-labelα-expansionImage 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 α-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.Federal University of Bahia Intelligent Vision Research LabVORTEX-CoLabSão Paulo State UniversitySão Paulo State UniversityUniversidade Federal da Bahia (UFBA)VORTEX-CoLabUniversidade Estadual Paulista (UNESP)Fontinele, JeffersonMendonca, MarceloRuiz, MarcoPapa, Joao [UNESP]Oliveira, Luciano2022-04-28T19:29:29Z2022-04-28T19:29:29Z2020-07-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/IJCNN48605.2020.9207032Proceedings of the International Joint Conference on Neural Networks.http://hdl.handle.net/11449/22159210.1109/IJCNN48605.2020.92070322-s2.0-85093828760Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings of the International Joint Conference on Neural Networksinfo:eu-repo/semantics/openAccess2022-04-28T19:29:29Zoai:repositorio.unesp.br:11449/221592Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:45:24.694099Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Faster α-expansion via dynamic programming and image partitioning |
title |
Faster α-expansion via dynamic programming and image partitioning |
spellingShingle |
Faster α-expansion via dynamic programming and image partitioning Fontinele, Jefferson dynamic programming image segmentation multi-label α-expansion |
title_short |
Faster α-expansion via dynamic programming and image partitioning |
title_full |
Faster α-expansion via dynamic programming and image partitioning |
title_fullStr |
Faster α-expansion via dynamic programming and image partitioning |
title_full_unstemmed |
Faster α-expansion via dynamic programming and image partitioning |
title_sort |
Faster α-expansion via dynamic programming and image partitioning |
author |
Fontinele, Jefferson |
author_facet |
Fontinele, Jefferson Mendonca, Marcelo Ruiz, Marco Papa, Joao [UNESP] Oliveira, Luciano |
author_role |
author |
author2 |
Mendonca, Marcelo Ruiz, Marco Papa, Joao [UNESP] Oliveira, Luciano |
author2_role |
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 |
dc.subject.por.fl_str_mv |
dynamic programming image segmentation multi-label α-expansion |
topic |
dynamic programming image segmentation multi-label α-expansion |
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 α-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 |
2020-07-01 2022-04-28T19:29:29Z 2022-04-28T19:29:29Z |
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 |
http://dx.doi.org/10.1109/IJCNN48605.2020.9207032 Proceedings of the International Joint Conference on Neural Networks. http://hdl.handle.net/11449/221592 10.1109/IJCNN48605.2020.9207032 2-s2.0-85093828760 |
url |
http://dx.doi.org/10.1109/IJCNN48605.2020.9207032 http://hdl.handle.net/11449/221592 |
identifier_str_mv |
Proceedings of the International Joint Conference on Neural Networks. 10.1109/IJCNN48605.2020.9207032 2-s2.0-85093828760 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings of the International Joint Conference on Neural Networks |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus 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_ |
1808128697061867520 |