Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s10669-020-09769-w http://hdl.handle.net/11449/221461 |
Resumo: | Morphological characteristics are still the most used tools for the identification of plant species. In this context, leaves are the most available plant organ used, given their perenniality and diversity. Computer-based image analysis help extract morphological features for botanical identification and maybe a solution to taxonomic problems requiring extensively trained specialists that use visual identification as the primary method for this approach. In this study, were collected 40 leaves from 30 trees and shrub species from 19 different families. Here, we compared two popular image capture devices: a scanner and a mobile phone. Features analyzed comprised color, shape, and texture. The performance of both devices was compared through three machine learning algorithms (adaptive boosting—AdaBoost, random forest, support vector machine—SVM) and an artificial neural network model (deep learning). Computer vision showed to be efficient in the identification of species (higher than 93%), with similar results obtained for both mobile phones and scanners. The algorithms SVM, random forest and deep learning performed more efficiently than AdaBoost. Based on the results, we present the Inovtaxon Plant Species Identification Software, available at https://github.com/DeborahBambil/Inovtaxon. |
id |
UNSP_c059db5948f4c119c1a5719963d434b1 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/221461 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networksComputer visionDeep learningInovtaxonMachine learningMorphologyNeural networksTaxonomyMorphological characteristics are still the most used tools for the identification of plant species. In this context, leaves are the most available plant organ used, given their perenniality and diversity. Computer-based image analysis help extract morphological features for botanical identification and maybe a solution to taxonomic problems requiring extensively trained specialists that use visual identification as the primary method for this approach. In this study, were collected 40 leaves from 30 trees and shrub species from 19 different families. Here, we compared two popular image capture devices: a scanner and a mobile phone. Features analyzed comprised color, shape, and texture. The performance of both devices was compared through three machine learning algorithms (adaptive boosting—AdaBoost, random forest, support vector machine—SVM) and an artificial neural network model (deep learning). Computer vision showed to be efficient in the identification of species (higher than 93%), with similar results obtained for both mobile phones and scanners. The algorithms SVM, random forest and deep learning performed more efficiently than AdaBoost. Based on the results, we present the Inovtaxon Plant Species Identification Software, available at https://github.com/DeborahBambil/Inovtaxon.Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do SulDepartment of Plant Biology Federal University of Mato Grosso do Sul (UFMS)Department of Cell Biology University of Brasília (UnB)Catholic University Dom BoscoBioscience Institute São Paulo State UniversityDirectory of Informatics Mato Grosso do Sul State UniversityDepartment of Botany UnBEmbrapa PantanalFederal University of Mato GrossoBioscience Institute São Paulo State UniversityUniversidade Federal de Mato Grosso do Sul (UFMS)University of Brasília (UnB)Catholic University Dom BoscoUniversidade Estadual Paulista (UNESP)Mato Grosso do Sul State UniversityUnBEmpresa Brasileira de Pesquisa Agropecuária (EMBRAPA)Federal University of Mato GrossoBambil, DeborahPistori, HemersonBao, Francielli [UNESP]Weber, VanessaAlves, Flávio MacedoGonçalves, Eduardo Gomesde Alencar Figueiredo, Lúcio FlávioAbreu, Urbano G. P.Arruda, RafaelBortolotto, Ieda Maria2022-04-28T19:28:35Z2022-04-28T19:28:35Z2020-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article480-484http://dx.doi.org/10.1007/s10669-020-09769-wEnvironment Systems and Decisions, v. 40, n. 4, p. 480-484, 2020.2194-54112194-5403http://hdl.handle.net/11449/22146110.1007/s10669-020-09769-w2-s2.0-85083461863Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEnvironment Systems and Decisionsinfo:eu-repo/semantics/openAccess2022-04-28T19:28:35Zoai:repositorio.unesp.br:11449/221461Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-28T19:28:35Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
title |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
spellingShingle |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks Bambil, Deborah Computer vision Deep learning Inovtaxon Machine learning Morphology Neural networks Taxonomy |
title_short |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
title_full |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
title_fullStr |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
title_full_unstemmed |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
title_sort |
Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks |
author |
Bambil, Deborah |
author_facet |
Bambil, Deborah Pistori, Hemerson Bao, Francielli [UNESP] Weber, Vanessa Alves, Flávio Macedo Gonçalves, Eduardo Gomes de Alencar Figueiredo, Lúcio Flávio Abreu, Urbano G. P. Arruda, Rafael Bortolotto, Ieda Maria |
author_role |
author |
author2 |
Pistori, Hemerson Bao, Francielli [UNESP] Weber, Vanessa Alves, Flávio Macedo Gonçalves, Eduardo Gomes de Alencar Figueiredo, Lúcio Flávio Abreu, Urbano G. P. Arruda, Rafael Bortolotto, Ieda Maria |
author2_role |
author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Mato Grosso do Sul (UFMS) University of Brasília (UnB) Catholic University Dom Bosco Universidade Estadual Paulista (UNESP) Mato Grosso do Sul State University UnB Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA) Federal University of Mato Grosso |
dc.contributor.author.fl_str_mv |
Bambil, Deborah Pistori, Hemerson Bao, Francielli [UNESP] Weber, Vanessa Alves, Flávio Macedo Gonçalves, Eduardo Gomes de Alencar Figueiredo, Lúcio Flávio Abreu, Urbano G. P. Arruda, Rafael Bortolotto, Ieda Maria |
dc.subject.por.fl_str_mv |
Computer vision Deep learning Inovtaxon Machine learning Morphology Neural networks Taxonomy |
topic |
Computer vision Deep learning Inovtaxon Machine learning Morphology Neural networks Taxonomy |
description |
Morphological characteristics are still the most used tools for the identification of plant species. In this context, leaves are the most available plant organ used, given their perenniality and diversity. Computer-based image analysis help extract morphological features for botanical identification and maybe a solution to taxonomic problems requiring extensively trained specialists that use visual identification as the primary method for this approach. In this study, were collected 40 leaves from 30 trees and shrub species from 19 different families. Here, we compared two popular image capture devices: a scanner and a mobile phone. Features analyzed comprised color, shape, and texture. The performance of both devices was compared through three machine learning algorithms (adaptive boosting—AdaBoost, random forest, support vector machine—SVM) and an artificial neural network model (deep learning). Computer vision showed to be efficient in the identification of species (higher than 93%), with similar results obtained for both mobile phones and scanners. The algorithms SVM, random forest and deep learning performed more efficiently than AdaBoost. Based on the results, we present the Inovtaxon Plant Species Identification Software, available at https://github.com/DeborahBambil/Inovtaxon. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-01 2022-04-28T19:28:35Z 2022-04-28T19:28:35Z |
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/10.1007/s10669-020-09769-w Environment Systems and Decisions, v. 40, n. 4, p. 480-484, 2020. 2194-5411 2194-5403 http://hdl.handle.net/11449/221461 10.1007/s10669-020-09769-w 2-s2.0-85083461863 |
url |
http://dx.doi.org/10.1007/s10669-020-09769-w http://hdl.handle.net/11449/221461 |
identifier_str_mv |
Environment Systems and Decisions, v. 40, n. 4, p. 480-484, 2020. 2194-5411 2194-5403 10.1007/s10669-020-09769-w 2-s2.0-85083461863 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Environment Systems and Decisions |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
480-484 |
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_ |
1797790154858954752 |