Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification

Detalhes bibliográficos
Autor(a) principal: Bressane, Adriano [UNESP]
Data de Publicação: 2016
Outros Autores: Roveda, Jos� Arnaldo Frutuoso [UNESP], Martins, Antonio Cesar Germano [UNESP]
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1109/LA-CCI.2015.7435983
http://hdl.handle.net/11449/168673
Resumo: Tree species identification is required for many applications. However, current techniques are dependent on the presence of morphological structures such as leaves, which restricts its use in certain situations and seasons. In this context, the use of trunk images can be an alternative. Therefore, the present study developed a pattern recognition based on co-occurrence descriptors, aiming evaluate its performance in the identification of 8 tree species from the Brazilian deciduous native forest, achieving promising results, with precision better than 0.8 for most of them, accuracy equivalent to 0.77 and average area under curve by Receiver Operating Characteristic of 0.88, during the tests with cross-validation sets.
id UNSP_8eaa349bdfe02f97e414a6d77a2affb3
oai_identifier_str oai:repositorio.unesp.br:11449/168673
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identificationBrazilian forestCo-occurrence descriptorsDecision TreeImage processingTrunk imagesTree species identification is required for many applications. However, current techniques are dependent on the presence of morphological structures such as leaves, which restricts its use in certain situations and seasons. In this context, the use of trunk images can be an alternative. Therefore, the present study developed a pattern recognition based on co-occurrence descriptors, aiming evaluate its performance in the identification of 8 tree species from the Brazilian deciduous native forest, achieving promising results, with precision better than 0.8 for most of them, accuracy equivalent to 0.77 and average area under curve by Receiver Operating Characteristic of 0.88, during the tests with cross-validation sets.Environmental Sciences Graduate Program UNESP - Univ. Estadual PaulistaEnvironmental Sciences Graduate Program UNESP - Univ. Estadual PaulistaUniversidade Estadual Paulista (Unesp)Bressane, Adriano [UNESP]Roveda, Jos� Arnaldo Frutuoso [UNESP]Martins, Antonio Cesar Germano [UNESP]2018-12-11T16:42:28Z2018-12-11T16:42:28Z2016-03-17info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1109/LA-CCI.2015.74359832015 Latin-America Congress on Computational Intelligence, LA-CCI 2015.http://hdl.handle.net/11449/16867310.1109/LA-CCI.2015.74359832-s2.0-8496962594189596375594042060000-0002-4899-3983Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2015 Latin-America Congress on Computational Intelligence, LA-CCI 2015info:eu-repo/semantics/openAccess2021-10-23T21:47:02Zoai:repositorio.unesp.br:11449/168673Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:43:37.701755Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
title Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
spellingShingle Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
Bressane, Adriano [UNESP]
Brazilian forest
Co-occurrence descriptors
Decision Tree
Image processing
Trunk images
title_short Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
title_full Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
title_fullStr Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
title_full_unstemmed Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
title_sort Pattern recognition in trunk images based on co-occurrence descriptors: A proposal applied to tree species identification
author Bressane, Adriano [UNESP]
author_facet Bressane, Adriano [UNESP]
Roveda, Jos� Arnaldo Frutuoso [UNESP]
Martins, Antonio Cesar Germano [UNESP]
author_role author
author2 Roveda, Jos� Arnaldo Frutuoso [UNESP]
Martins, Antonio Cesar Germano [UNESP]
author2_role author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Bressane, Adriano [UNESP]
Roveda, Jos� Arnaldo Frutuoso [UNESP]
Martins, Antonio Cesar Germano [UNESP]
dc.subject.por.fl_str_mv Brazilian forest
Co-occurrence descriptors
Decision Tree
Image processing
Trunk images
topic Brazilian forest
Co-occurrence descriptors
Decision Tree
Image processing
Trunk images
description Tree species identification is required for many applications. However, current techniques are dependent on the presence of morphological structures such as leaves, which restricts its use in certain situations and seasons. In this context, the use of trunk images can be an alternative. Therefore, the present study developed a pattern recognition based on co-occurrence descriptors, aiming evaluate its performance in the identification of 8 tree species from the Brazilian deciduous native forest, achieving promising results, with precision better than 0.8 for most of them, accuracy equivalent to 0.77 and average area under curve by Receiver Operating Characteristic of 0.88, during the tests with cross-validation sets.
publishDate 2016
dc.date.none.fl_str_mv 2016-03-17
2018-12-11T16:42:28Z
2018-12-11T16:42:28Z
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/LA-CCI.2015.7435983
2015 Latin-America Congress on Computational Intelligence, LA-CCI 2015.
http://hdl.handle.net/11449/168673
10.1109/LA-CCI.2015.7435983
2-s2.0-84969625941
8959637559404206
0000-0002-4899-3983
url http://dx.doi.org/10.1109/LA-CCI.2015.7435983
http://hdl.handle.net/11449/168673
identifier_str_mv 2015 Latin-America Congress on Computational Intelligence, LA-CCI 2015.
10.1109/LA-CCI.2015.7435983
2-s2.0-84969625941
8959637559404206
0000-0002-4899-3983
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2015 Latin-America Congress on Computational Intelligence, LA-CCI 2015
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_ 1808128691858833408