Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.14483/2256201X.16700 http://hdl.handle.net/11449/221625 |
Resumo: | Field deployable computer vision wood identification systems can be relevant in combating illegal logging in the real world. This work used 764 xylarium specimens from 84 taxa to develop an image data set to train a classifier and identify 14 commercial Colombian timbers. We took images of specimens from various xylaria outside Colombia, trained and evaluated an initial identification model and then collected additional images from a Colombian xylarium (BOFw) and incorporated these images to refine and produce a final model. The specimen classification accuracy of this final model was ~ 97%, which demonstrates that including local specimens can augment the accuracy and reliability of the XyloTron system. Our study demonstrates the first deployable computer vision model for wood identification in Colombia, which is developed on a timescale of months rather than years by leveraging on international cooperation. We conclude that field testing and advanced forensic and machine learning training are the next logical steps. |
id |
UNSP_cb5e607b6f8a7b2d2ed40854e3900cb6 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/221625 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnershipIdentificación de maderas colombianas utilizando el Xylotron: Prueba de concepto de una colaboración internacionalDeep learningForensic wood anatomyMachine LearningTransfer learningWood identificationField deployable computer vision wood identification systems can be relevant in combating illegal logging in the real world. This work used 764 xylarium specimens from 84 taxa to develop an image data set to train a classifier and identify 14 commercial Colombian timbers. We took images of specimens from various xylaria outside Colombia, trained and evaluated an initial identification model and then collected additional images from a Colombian xylarium (BOFw) and incorporated these images to refine and produce a final model. The specimen classification accuracy of this final model was ~ 97%, which demonstrates that including local specimens can augment the accuracy and reliability of the XyloTron system. Our study demonstrates the first deployable computer vision model for wood identification in Colombia, which is developed on a timescale of months rather than years by leveraging on international cooperation. We conclude that field testing and advanced forensic and machine learning training are the next logical steps.Department of Botany University of WisconsinCenter for Wood Anatomy Research USDA Forest Service Forest Products LaboratoryFacultad de Medio Ambiente y Recursos Naturales Universidad Distrital Francisco Jose de CaldasDISAFA University of Torino, Largo Paolo Braccini 2Department of Forestry and Natural Resources Purdue UniversityDepartamento de Ciências Biolôgicas (Botânica) Universidade Estadual PaulistaDepartment of Sustainable Bioproducts Mississippi State UniversityDepartamento de Ciências Biolôgicas (Botânica) Universidade Estadual PaulistaUniversity of WisconsinForest Products LaboratoryUniversidad Distrital Francisco Jose de CaldasUniversity of TorinoPurdue UniversityUniversidade Estadual Paulista (UNESP)Mississippi State UniversityArévalo, RafaelPulido R., Esperanza N.Solórzano G., Juan F.Soares, RichardRuffinatto, FlavioRavindran, PrabuWiedenhoeft, Alex C. [UNESP]2022-04-28T19:29:49Z2022-04-28T19:29:49Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article5-16http://dx.doi.org/10.14483/2256201X.16700Colombia Forestal, v. 24, n. 1, p. 5-16, 2021.2256-201X0120-0739http://hdl.handle.net/11449/22162510.14483/2256201X.167002-s2.0-85097230568Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengColombia Forestalinfo:eu-repo/semantics/openAccess2022-04-28T19:29:49Zoai:repositorio.unesp.br:11449/221625Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T23:21:47.866966Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership Identificación de maderas colombianas utilizando el Xylotron: Prueba de concepto de una colaboración internacional |
title |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
spellingShingle |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership Arévalo, Rafael Deep learning Forensic wood anatomy Machine Learning Transfer learning Wood identification |
title_short |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
title_full |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
title_fullStr |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
title_full_unstemmed |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
title_sort |
Imaged based identification of colombian timbers using the xylotron: A proof of concept international partnership |
author |
Arévalo, Rafael |
author_facet |
Arévalo, Rafael Pulido R., Esperanza N. Solórzano G., Juan F. Soares, Richard Ruffinatto, Flavio Ravindran, Prabu Wiedenhoeft, Alex C. [UNESP] |
author_role |
author |
author2 |
Pulido R., Esperanza N. Solórzano G., Juan F. Soares, Richard Ruffinatto, Flavio Ravindran, Prabu Wiedenhoeft, Alex C. [UNESP] |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
University of Wisconsin Forest Products Laboratory Universidad Distrital Francisco Jose de Caldas University of Torino Purdue University Universidade Estadual Paulista (UNESP) Mississippi State University |
dc.contributor.author.fl_str_mv |
Arévalo, Rafael Pulido R., Esperanza N. Solórzano G., Juan F. Soares, Richard Ruffinatto, Flavio Ravindran, Prabu Wiedenhoeft, Alex C. [UNESP] |
dc.subject.por.fl_str_mv |
Deep learning Forensic wood anatomy Machine Learning Transfer learning Wood identification |
topic |
Deep learning Forensic wood anatomy Machine Learning Transfer learning Wood identification |
description |
Field deployable computer vision wood identification systems can be relevant in combating illegal logging in the real world. This work used 764 xylarium specimens from 84 taxa to develop an image data set to train a classifier and identify 14 commercial Colombian timbers. We took images of specimens from various xylaria outside Colombia, trained and evaluated an initial identification model and then collected additional images from a Colombian xylarium (BOFw) and incorporated these images to refine and produce a final model. The specimen classification accuracy of this final model was ~ 97%, which demonstrates that including local specimens can augment the accuracy and reliability of the XyloTron system. Our study demonstrates the first deployable computer vision model for wood identification in Colombia, which is developed on a timescale of months rather than years by leveraging on international cooperation. We conclude that field testing and advanced forensic and machine learning training are the next logical steps. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 2022-04-28T19:29:49Z 2022-04-28T19:29:49Z |
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/10.14483/2256201X.16700 Colombia Forestal, v. 24, n. 1, p. 5-16, 2021. 2256-201X 0120-0739 http://hdl.handle.net/11449/221625 10.14483/2256201X.16700 2-s2.0-85097230568 |
url |
http://dx.doi.org/10.14483/2256201X.16700 http://hdl.handle.net/11449/221625 |
identifier_str_mv |
Colombia Forestal, v. 24, n. 1, p. 5-16, 2021. 2256-201X 0120-0739 10.14483/2256201X.16700 2-s2.0-85097230568 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Colombia Forestal |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
5-16 |
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_ |
1808129510342656000 |