Proposal of automated computational method to support Virginia tobacco classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019001000782 |
Resumo: | ABSTRACT This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. |
id |
UFCG-1_897d4e634714a0aec58deb0dbba079e4 |
---|---|
oai_identifier_str |
oai:scielo:S1415-43662019001000782 |
network_acronym_str |
UFCG-1 |
network_name_str |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
repository_id_str |
|
spelling |
Proposal of automated computational method to support Virginia tobacco classificationimage processingpartial least squareartificial neural networkABSTRACT This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively.Departamento de Engenharia Agrícola - UFCG2019-10-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019001000782Revista Brasileira de Engenharia Agrícola e Ambiental v.23 n.10 2019reponame:Revista Brasileira de Engenharia Agrícola e Ambiental (Online)instname:Universidade Federal de Campina Grande (UFCG)instacron:UFCG10.1590/1807-1929/agriambi.v23n10p782-786info:eu-repo/semantics/openAccessTedesco,Leonel P. C.Freitas,Adriano da C. deMolz,Rolf F.Schreiber,Jacques N. C.eng2019-09-03T00:00:00Zoai:scielo:S1415-43662019001000782Revistahttp://www.scielo.br/rbeaaPUBhttps://old.scielo.br/oai/scielo-oai.php||agriambi@agriambi.com.br1807-19291415-4366opendoar:2019-09-03T00:00Revista Brasileira de Engenharia Agrícola e Ambiental (Online) - Universidade Federal de Campina Grande (UFCG)false |
dc.title.none.fl_str_mv |
Proposal of automated computational method to support Virginia tobacco classification |
title |
Proposal of automated computational method to support Virginia tobacco classification |
spellingShingle |
Proposal of automated computational method to support Virginia tobacco classification Tedesco,Leonel P. C. image processing partial least square artificial neural network |
title_short |
Proposal of automated computational method to support Virginia tobacco classification |
title_full |
Proposal of automated computational method to support Virginia tobacco classification |
title_fullStr |
Proposal of automated computational method to support Virginia tobacco classification |
title_full_unstemmed |
Proposal of automated computational method to support Virginia tobacco classification |
title_sort |
Proposal of automated computational method to support Virginia tobacco classification |
author |
Tedesco,Leonel P. C. |
author_facet |
Tedesco,Leonel P. C. Freitas,Adriano da C. de Molz,Rolf F. Schreiber,Jacques N. C. |
author_role |
author |
author2 |
Freitas,Adriano da C. de Molz,Rolf F. Schreiber,Jacques N. C. |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Tedesco,Leonel P. C. Freitas,Adriano da C. de Molz,Rolf F. Schreiber,Jacques N. C. |
dc.subject.por.fl_str_mv |
image processing partial least square artificial neural network |
topic |
image processing partial least square artificial neural network |
description |
ABSTRACT This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019001000782 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1415-43662019001000782 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1807-1929/agriambi.v23n10p782-786 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Departamento de Engenharia Agrícola - UFCG |
publisher.none.fl_str_mv |
Departamento de Engenharia Agrícola - UFCG |
dc.source.none.fl_str_mv |
Revista Brasileira de Engenharia Agrícola e Ambiental v.23 n.10 2019 reponame:Revista Brasileira de Engenharia Agrícola e Ambiental (Online) instname:Universidade Federal de Campina Grande (UFCG) instacron:UFCG |
instname_str |
Universidade Federal de Campina Grande (UFCG) |
instacron_str |
UFCG |
institution |
UFCG |
reponame_str |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
collection |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) |
repository.name.fl_str_mv |
Revista Brasileira de Engenharia Agrícola e Ambiental (Online) - Universidade Federal de Campina Grande (UFCG) |
repository.mail.fl_str_mv |
||agriambi@agriambi.com.br |
_version_ |
1750297686954737664 |