Inducing Contextual Classifications with Kernel Functions into Support Vector Machines

Detalhes bibliográficos
Autor(a) principal: Negri, Rogério Galante [UNESP]
Data de Publicação: 2018
Outros Autores: Da Silva, Erivaldo Antônio [UNESP], Casaca, Wallace [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/LGRS.2018.2816460
http://hdl.handle.net/11449/176360
Resumo: Kernel functions have revolutionized theory and practice in the field of pattern recognition, especially to perform image classification. Besides giving rise to nonlinear variants of the well-known support vector machine (SVM), these functions have also been successfully used to classify nonvectorial data (e.g., graphs and collection of sets), in which customized metrics are created to precisely measure the similarity among such contextual data entities. This letter introduces two context-inspired kernel functions as new SVM-driven methods for remote sensing image classification. In contrast to the existing SVM-based approaches that assume only multiattribute vectors as representative features in a high-dimensional space, the proposed models formally establish comparisons between the entire sets of context-given data, thus employing these contextual measurements to drive the classification. More precisely, stochastic distances as well as hypothesis tests are conveniently handled and 'kernelized' to build our models. A complete battery of experiments involving both remote sensing and real-world images is conducted to validate the performance of the proposed kernels against various well-established SVM-based methods.
id UNSP_297543f7b8562290e273fc9eafb2f883
oai_identifier_str oai:repositorio.unesp.br:11449/176360
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Inducing Contextual Classifications with Kernel Functions into Support Vector MachinesContextimage classificationKernel functionsKernel functions have revolutionized theory and practice in the field of pattern recognition, especially to perform image classification. Besides giving rise to nonlinear variants of the well-known support vector machine (SVM), these functions have also been successfully used to classify nonvectorial data (e.g., graphs and collection of sets), in which customized metrics are created to precisely measure the similarity among such contextual data entities. This letter introduces two context-inspired kernel functions as new SVM-driven methods for remote sensing image classification. In contrast to the existing SVM-based approaches that assume only multiattribute vectors as representative features in a high-dimensional space, the proposed models formally establish comparisons between the entire sets of context-given data, thus employing these contextual measurements to drive the classification. More precisely, stochastic distances as well as hypothesis tests are conveniently handled and 'kernelized' to build our models. A complete battery of experiments involving both remote sensing and real-world images is conducted to validate the performance of the proposed kernels against various well-established SVM-based methods.Instituto de Ciência e Tecnologia UNESPFaculdade de Ciência e Tecnologia UNESPCampus Experimental de Rosana UNESPInstituto de Ciência e Tecnologia UNESPFaculdade de Ciência e Tecnologia UNESPCampus Experimental de Rosana UNESPUniversidade Estadual Paulista (Unesp)Negri, Rogério Galante [UNESP]Da Silva, Erivaldo Antônio [UNESP]Casaca, Wallace [UNESP]2018-12-11T17:20:29Z2018-12-11T17:20:29Z2018-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article962-966application/pdfhttp://dx.doi.org/10.1109/LGRS.2018.2816460IEEE Geoscience and Remote Sensing Letters, v. 15, n. 6, p. 962-966, 2018.1545-598Xhttp://hdl.handle.net/11449/17636010.1109/LGRS.2018.28164602-s2.0-850473978772-s2.0-85047397877.pdf82018051329812880000-0002-4808-2362Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIEEE Geoscience and Remote Sensing Lettersinfo:eu-repo/semantics/openAccess2024-08-06T18:56:04Zoai:repositorio.unesp.br:11449/176360Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T18:56:04Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
title Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
spellingShingle Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
Negri, Rogério Galante [UNESP]
Context
image classification
Kernel functions
title_short Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
title_full Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
title_fullStr Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
title_full_unstemmed Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
title_sort Inducing Contextual Classifications with Kernel Functions into Support Vector Machines
author Negri, Rogério Galante [UNESP]
author_facet Negri, Rogério Galante [UNESP]
Da Silva, Erivaldo Antônio [UNESP]
Casaca, Wallace [UNESP]
author_role author
author2 Da Silva, Erivaldo Antônio [UNESP]
Casaca, Wallace [UNESP]
author2_role author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Negri, Rogério Galante [UNESP]
Da Silva, Erivaldo Antônio [UNESP]
Casaca, Wallace [UNESP]
dc.subject.por.fl_str_mv Context
image classification
Kernel functions
topic Context
image classification
Kernel functions
description Kernel functions have revolutionized theory and practice in the field of pattern recognition, especially to perform image classification. Besides giving rise to nonlinear variants of the well-known support vector machine (SVM), these functions have also been successfully used to classify nonvectorial data (e.g., graphs and collection of sets), in which customized metrics are created to precisely measure the similarity among such contextual data entities. This letter introduces two context-inspired kernel functions as new SVM-driven methods for remote sensing image classification. In contrast to the existing SVM-based approaches that assume only multiattribute vectors as representative features in a high-dimensional space, the proposed models formally establish comparisons between the entire sets of context-given data, thus employing these contextual measurements to drive the classification. More precisely, stochastic distances as well as hypothesis tests are conveniently handled and 'kernelized' to build our models. A complete battery of experiments involving both remote sensing and real-world images is conducted to validate the performance of the proposed kernels against various well-established SVM-based methods.
publishDate 2018
dc.date.none.fl_str_mv 2018-12-11T17:20:29Z
2018-12-11T17:20:29Z
2018-06-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1109/LGRS.2018.2816460
IEEE Geoscience and Remote Sensing Letters, v. 15, n. 6, p. 962-966, 2018.
1545-598X
http://hdl.handle.net/11449/176360
10.1109/LGRS.2018.2816460
2-s2.0-85047397877
2-s2.0-85047397877.pdf
8201805132981288
0000-0002-4808-2362
url http://dx.doi.org/10.1109/LGRS.2018.2816460
http://hdl.handle.net/11449/176360
identifier_str_mv IEEE Geoscience and Remote Sensing Letters, v. 15, n. 6, p. 962-966, 2018.
1545-598X
10.1109/LGRS.2018.2816460
2-s2.0-85047397877
2-s2.0-85047397877.pdf
8201805132981288
0000-0002-4808-2362
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv IEEE Geoscience and Remote Sensing Letters
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 962-966
application/pdf
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_ 1808128210518409216