Residual spaces based on component trees: theory and applications
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da Uninove |
Texto Completo: | http://bibliotecatede.uninove.br/handle/tede/3093 |
Resumo: | This thesis presents a characterization (i.e., definitions, properties and algorithms) of residual spaces obtained from spaces of primitives based on component trees. Residual spaces are hierarchical structures constructed from image regions from which we can perform image analysis efficiently. For that, we can analyze residual regions by means of its maximum residual values leading to the called maximum residual operators. Although such operators extract relevant information, they do not take into account the hierarchy of the residual spaces, which means that they may extract residues from undesirable regions. In another point of view, in this thesis we present a novel approach to analyze residual spaces through a hierarchical structure called resid- ual tree. From this structure, we extract attribute vectors to build a machine learning model which gives a matching value between ground truth regions and residual tree nodes (or regions). After, from the selected residual tree nodes, we present a new approach to choose the best residual nodes. Finally, we show that it is a solution to the residual space analysis problem. In order to evaluate our new approach, some experiments were carried out with a plant dataset and results report the state-of-the-art performance in plant detection and segmentation. |
id |
NOVE_93a4ed00a093f42847124345e7ce987a |
---|---|
oai_identifier_str |
oai:localhost:tede/3093 |
network_acronym_str |
NOVE |
network_name_str |
Biblioteca Digital de Teses e Dissertações da Uninove |
repository_id_str |
|
spelling |
Alves, Wonder Alexandre Luzhttp://lattes.cnpq.br/3138898469532698Alves, Wonder Alexandre Luzhttp://lattes.cnpq.br/3138898469532698Araújo, Sidnei Alves dehttp://lattes.cnpq.br/2542529753132844Hashimoto, Ronaldo Fumiohttp://lattes.cnpq.br/9283304583756076Mesquita, Marcos Eduardo Ribeiro do Vallehttp://lattes.cnpq.br/7809380690711656Guimarães, Silvio Jamil Ferzolihttp://lattes.cnpq.br/8522089151904453http://lattes.cnpq.br/6396202937482737Gobber, Charles Ferreira2022-11-17T19:29:01Z2021-03-04Gobber, Charles Ferreira. Residual spaces based on component trees: theory and applications. 2021. 94 f. Tese( Programa de Pós-Graduação em Informática e Gestão do Conhecimento) - Universidade Nove de Julho, São Paulo.http://bibliotecatede.uninove.br/handle/tede/3093This thesis presents a characterization (i.e., definitions, properties and algorithms) of residual spaces obtained from spaces of primitives based on component trees. Residual spaces are hierarchical structures constructed from image regions from which we can perform image analysis efficiently. For that, we can analyze residual regions by means of its maximum residual values leading to the called maximum residual operators. Although such operators extract relevant information, they do not take into account the hierarchy of the residual spaces, which means that they may extract residues from undesirable regions. In another point of view, in this thesis we present a novel approach to analyze residual spaces through a hierarchical structure called resid- ual tree. From this structure, we extract attribute vectors to build a machine learning model which gives a matching value between ground truth regions and residual tree nodes (or regions). After, from the selected residual tree nodes, we present a new approach to choose the best residual nodes. Finally, we show that it is a solution to the residual space analysis problem. In order to evaluate our new approach, some experiments were carried out with a plant dataset and results report the state-of-the-art performance in plant detection and segmentation.Esta tese apresenta uma caracterização (i.e., definições, propriedades e algoritmos) de espaços de resíduos obtidos a partir de espaços de primitivas baseados em árvores de componentes. Espaços de resíduos são estruturas hierárquicas construídas de regiões de imagens das quais podemos realizar análise de imagens eficientemente. Para isto, podemos analisar as regiões de resíduos por meio de seus valores maximais levando aos chamados operadores de máximos resíduos. Apesar de tais operadores extraírem informações relevantes, eles não consideram a hierarquia dos espaços de resíduos, o que significa que eles podem extrair resíduos de regiões indesejáveis. Por outro ponto de vista, nesta tese apresentamos uma nova abordagem para analisar espaços de resíduos através de uma estrutura hierárquica chamada de árvore de resíduos. A partir dessa estrutura, extraímos vetores de atributos para construir um modelo de aprendizado de máquinas do qual fornece um valor de correspondência entre regiões conhecidas e nodes (ou regiões) de árvores de resíduos. Posteriormente, a partir dos nodes selecionados da árvore de resíduos, nós apresentamos uma nova abordagem para escolher os melhores nodes residuais. Finalmente, nós mostramos que essa é uma solução para o problema de análise do espaço de resíduos. No intuito de avaliar nossa nova abordagem, alguns experimentos foram conduzidos com um dataset de plantas e os resultados reportam o estado da arte em detecção e segmentação de plantas.Submitted by Nadir Basilio (nadirsb@uninove.br) on 2022-11-17T19:29:01Z No. of bitstreams: 1 Charles Ferreira Gobber.pdf: 24287138 bytes, checksum: 287f61d5ac5e237c389bac5bb9766112 (MD5)Made available in DSpace on 2022-11-17T19:29:01Z (GMT). No. of bitstreams: 1 Charles Ferreira Gobber.pdf: 24287138 bytes, checksum: 287f61d5ac5e237c389bac5bb9766112 (MD5) Previous issue date: 2021-03-04application/pdfengUniversidade Nove de JulhoPrograma de Pós-Graduação em Informática e Gestão do ConhecimentoUNINOVEBrasilInformáticaespaços de resíduosespaços de primitivasoperadores residuaisárvores de componentesárvores de resíduosaprendizagem de máquinasresidual spacesspaces of primitivesresidual operatorscomponent treesresidual treesmachine learningCIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAOResidual spaces based on component trees: theory and applicationsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesis8930092515683771531600info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da Uninoveinstname:Universidade Nove de Julho (UNINOVE)instacron:UNINOVEORIGINALCharles Ferreira Gobber.pdfCharles Ferreira Gobber.pdfapplication/pdf24287138http://localhost:8080/tede/bitstream/tede/3093/2/Charles+Ferreira+Gobber.pdf287f61d5ac5e237c389bac5bb9766112MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82165http://localhost:8080/tede/bitstream/tede/3093/1/license.txtbd3efa91386c1718a7f26a329fdcb468MD51tede/30932022-11-17 16:29:01.587oai:localhost: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Biblioteca Digital de Teses e Dissertaçõeshttp://bibliotecatede.uninove.br/PRIhttp://bibliotecatede.uninove.br/oai/requestbibliotecatede@uninove.br||bibliotecatede@uninove.bropendoar:2022-11-17T19:29:01Biblioteca Digital de Teses e Dissertações da Uninove - Universidade Nove de Julho (UNINOVE)false |
dc.title.por.fl_str_mv |
Residual spaces based on component trees: theory and applications |
title |
Residual spaces based on component trees: theory and applications |
spellingShingle |
Residual spaces based on component trees: theory and applications Gobber, Charles Ferreira espaços de resíduos espaços de primitivas operadores residuais árvores de componentes árvores de resíduos aprendizagem de máquinas residual spaces spaces of primitives residual operators component trees residual trees machine learning CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
title_short |
Residual spaces based on component trees: theory and applications |
title_full |
Residual spaces based on component trees: theory and applications |
title_fullStr |
Residual spaces based on component trees: theory and applications |
title_full_unstemmed |
Residual spaces based on component trees: theory and applications |
title_sort |
Residual spaces based on component trees: theory and applications |
author |
Gobber, Charles Ferreira |
author_facet |
Gobber, Charles Ferreira |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Alves, Wonder Alexandre Luz |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/3138898469532698 |
dc.contributor.referee1.fl_str_mv |
Alves, Wonder Alexandre Luz |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/3138898469532698 |
dc.contributor.referee2.fl_str_mv |
Araújo, Sidnei Alves de |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/2542529753132844 |
dc.contributor.referee3.fl_str_mv |
Hashimoto, Ronaldo Fumio |
dc.contributor.referee3Lattes.fl_str_mv |
http://lattes.cnpq.br/9283304583756076 |
dc.contributor.referee4.fl_str_mv |
Mesquita, Marcos Eduardo Ribeiro do Valle |
dc.contributor.referee4Lattes.fl_str_mv |
http://lattes.cnpq.br/7809380690711656 |
dc.contributor.referee5.fl_str_mv |
Guimarães, Silvio Jamil Ferzoli |
dc.contributor.referee5Lattes.fl_str_mv |
http://lattes.cnpq.br/8522089151904453 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/6396202937482737 |
dc.contributor.author.fl_str_mv |
Gobber, Charles Ferreira |
contributor_str_mv |
Alves, Wonder Alexandre Luz Alves, Wonder Alexandre Luz Araújo, Sidnei Alves de Hashimoto, Ronaldo Fumio Mesquita, Marcos Eduardo Ribeiro do Valle Guimarães, Silvio Jamil Ferzoli |
dc.subject.por.fl_str_mv |
espaços de resíduos espaços de primitivas operadores residuais árvores de componentes árvores de resíduos aprendizagem de máquinas |
topic |
espaços de resíduos espaços de primitivas operadores residuais árvores de componentes árvores de resíduos aprendizagem de máquinas residual spaces spaces of primitives residual operators component trees residual trees machine learning CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
dc.subject.eng.fl_str_mv |
residual spaces spaces of primitives residual operators component trees residual trees machine learning |
dc.subject.cnpq.fl_str_mv |
CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO |
description |
This thesis presents a characterization (i.e., definitions, properties and algorithms) of residual spaces obtained from spaces of primitives based on component trees. Residual spaces are hierarchical structures constructed from image regions from which we can perform image analysis efficiently. For that, we can analyze residual regions by means of its maximum residual values leading to the called maximum residual operators. Although such operators extract relevant information, they do not take into account the hierarchy of the residual spaces, which means that they may extract residues from undesirable regions. In another point of view, in this thesis we present a novel approach to analyze residual spaces through a hierarchical structure called resid- ual tree. From this structure, we extract attribute vectors to build a machine learning model which gives a matching value between ground truth regions and residual tree nodes (or regions). After, from the selected residual tree nodes, we present a new approach to choose the best residual nodes. Finally, we show that it is a solution to the residual space analysis problem. In order to evaluate our new approach, some experiments were carried out with a plant dataset and results report the state-of-the-art performance in plant detection and segmentation. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021-03-04 |
dc.date.accessioned.fl_str_mv |
2022-11-17T19:29:01Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
Gobber, Charles Ferreira. Residual spaces based on component trees: theory and applications. 2021. 94 f. Tese( Programa de Pós-Graduação em Informática e Gestão do Conhecimento) - Universidade Nove de Julho, São Paulo. |
dc.identifier.uri.fl_str_mv |
http://bibliotecatede.uninove.br/handle/tede/3093 |
identifier_str_mv |
Gobber, Charles Ferreira. Residual spaces based on component trees: theory and applications. 2021. 94 f. Tese( Programa de Pós-Graduação em Informática e Gestão do Conhecimento) - Universidade Nove de Julho, São Paulo. |
url |
http://bibliotecatede.uninove.br/handle/tede/3093 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.cnpq.fl_str_mv |
8930092515683771531 |
dc.relation.confidence.fl_str_mv |
600 |
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.publisher.none.fl_str_mv |
Universidade Nove de Julho |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Informática e Gestão do Conhecimento |
dc.publisher.initials.fl_str_mv |
UNINOVE |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Informática |
publisher.none.fl_str_mv |
Universidade Nove de Julho |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da Uninove instname:Universidade Nove de Julho (UNINOVE) instacron:UNINOVE |
instname_str |
Universidade Nove de Julho (UNINOVE) |
instacron_str |
UNINOVE |
institution |
UNINOVE |
reponame_str |
Biblioteca Digital de Teses e Dissertações da Uninove |
collection |
Biblioteca Digital de Teses e Dissertações da Uninove |
bitstream.url.fl_str_mv |
http://localhost:8080/tede/bitstream/tede/3093/2/Charles+Ferreira+Gobber.pdf http://localhost:8080/tede/bitstream/tede/3093/1/license.txt |
bitstream.checksum.fl_str_mv |
287f61d5ac5e237c389bac5bb9766112 bd3efa91386c1718a7f26a329fdcb468 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da Uninove - Universidade Nove de Julho (UNINOVE) |
repository.mail.fl_str_mv |
bibliotecatede@uninove.br||bibliotecatede@uninove.br |
_version_ |
1811016889058459648 |