Interactive Image Segmentation using Particle Competition and Cooperation

Detalhes bibliográficos
Autor(a) principal: Breve, Fabricio [UNESP]
Data de Publicação: 2015
Outros Autores: Quiles, Marcos Goncalves, Zhao, Liang, IEEE
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://hdl.handle.net/11449/161235
Resumo: Many interactive image processing approaches are based on semi-supervised learning, which employ both labeled and unlabeled data in its training process. In the interactive image segmentation problem, a human specialist labels some pixels of an object while the semi-supervised algorithm labels the remaining pixels of the segment. The particle competition and cooperation model is a recent graph-based semi-supervised learning approach. It employs particles walking in a graph to classify the data items corresponding to graph nodes. Each particle group aims to dominate most unlabeled nodes, spreading their label, and preventing enemy particles invasion. In this paper, the particle competition and cooperation model is extended to perform interactive image segmentation. Each image pixel is converted into a graph node, which is connected to its nearest neighbors according to their visual features and location in the original image. Labeled pixel generates particles that propagate their label to the unlabeled pixels. The particle model also takes the contributions from the adjacent pixels to classify less confident labeled pixels. Computer simulations are performed on real-world images, including images from the Microsoft GrabCut dataset, which allows a straightly comparison with other techniques. The segmentation results show the effectiveness of the proposed approach.
id UNSP_de59616ec45891cac4d0f2936d3e2f59
oai_identifier_str oai:repositorio.unesp.br:11449/161235
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Interactive Image Segmentation using Particle Competition and CooperationMany interactive image processing approaches are based on semi-supervised learning, which employ both labeled and unlabeled data in its training process. In the interactive image segmentation problem, a human specialist labels some pixels of an object while the semi-supervised algorithm labels the remaining pixels of the segment. The particle competition and cooperation model is a recent graph-based semi-supervised learning approach. It employs particles walking in a graph to classify the data items corresponding to graph nodes. Each particle group aims to dominate most unlabeled nodes, spreading their label, and preventing enemy particles invasion. In this paper, the particle competition and cooperation model is extended to perform interactive image segmentation. Each image pixel is converted into a graph node, which is connected to its nearest neighbors according to their visual features and location in the original image. Labeled pixel generates particles that propagate their label to the unlabeled pixels. The particle model also takes the contributions from the adjacent pixels to classify less confident labeled pixels. Computer simulations are performed on real-world images, including images from the Microsoft GrabCut dataset, which allows a straightly comparison with other techniques. The segmentation results show the effectiveness of the proposed approach.Sao Paulo State Univ UNESP, Inst Geosci & Exact Sci IGCE, Dept Stat Appl Math & Computat DEMAC, Sao Paulo, BrazilFed Univ Sao Paulo Unifesp, Inst Sci & Technol ICT, Sao Jose Dos Campos, SP, BrazilUniv Sao Paulo, Sch Philosophy Sci & Literature Ribeirao Preto FF, Dept Comp Sci & Math DCM, Sao Paulo, BrazilSao Paulo State Univ UNESP, Inst Geosci & Exact Sci IGCE, Dept Stat Appl Math & Computat DEMAC, Sao Paulo, BrazilIeeeUniversidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Breve, Fabricio [UNESP]Quiles, Marcos GoncalvesZhao, LiangIEEE2018-11-26T16:26:29Z2018-11-26T16:26:29Z2015-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject8application/pdf2015 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2015.2161-4393http://hdl.handle.net/11449/161235WOS:000370730602005WOS000370730602005.pdfWeb of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2015 International Joint Conference On Neural Networks (ijcnn)info:eu-repo/semantics/openAccess2024-01-18T06:24:14Zoai:repositorio.unesp.br:11449/161235Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T23:19:29.055268Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Interactive Image Segmentation using Particle Competition and Cooperation
title Interactive Image Segmentation using Particle Competition and Cooperation
spellingShingle Interactive Image Segmentation using Particle Competition and Cooperation
Breve, Fabricio [UNESP]
title_short Interactive Image Segmentation using Particle Competition and Cooperation
title_full Interactive Image Segmentation using Particle Competition and Cooperation
title_fullStr Interactive Image Segmentation using Particle Competition and Cooperation
title_full_unstemmed Interactive Image Segmentation using Particle Competition and Cooperation
title_sort Interactive Image Segmentation using Particle Competition and Cooperation
author Breve, Fabricio [UNESP]
author_facet Breve, Fabricio [UNESP]
Quiles, Marcos Goncalves
Zhao, Liang
IEEE
author_role author
author2 Quiles, Marcos Goncalves
Zhao, Liang
IEEE
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Universidade de São Paulo (USP)
dc.contributor.author.fl_str_mv Breve, Fabricio [UNESP]
Quiles, Marcos Goncalves
Zhao, Liang
IEEE
description Many interactive image processing approaches are based on semi-supervised learning, which employ both labeled and unlabeled data in its training process. In the interactive image segmentation problem, a human specialist labels some pixels of an object while the semi-supervised algorithm labels the remaining pixels of the segment. The particle competition and cooperation model is a recent graph-based semi-supervised learning approach. It employs particles walking in a graph to classify the data items corresponding to graph nodes. Each particle group aims to dominate most unlabeled nodes, spreading their label, and preventing enemy particles invasion. In this paper, the particle competition and cooperation model is extended to perform interactive image segmentation. Each image pixel is converted into a graph node, which is connected to its nearest neighbors according to their visual features and location in the original image. Labeled pixel generates particles that propagate their label to the unlabeled pixels. The particle model also takes the contributions from the adjacent pixels to classify less confident labeled pixels. Computer simulations are performed on real-world images, including images from the Microsoft GrabCut dataset, which allows a straightly comparison with other techniques. The segmentation results show the effectiveness of the proposed approach.
publishDate 2015
dc.date.none.fl_str_mv 2015-01-01
2018-11-26T16:26:29Z
2018-11-26T16:26:29Z
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 2015 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2015.
2161-4393
http://hdl.handle.net/11449/161235
WOS:000370730602005
WOS000370730602005.pdf
identifier_str_mv 2015 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2015.
2161-4393
WOS:000370730602005
WOS000370730602005.pdf
url http://hdl.handle.net/11449/161235
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2015 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
application/pdf
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_ 1808129507517792256