Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks

Determination of intramuscular fat (IMF) content in dry cured meats is critical because it affects the sensory quality and consumer's acceptability. Recently, deep learning has become one of the most promising techniques in machine learning for image analysis. However, few applications in food...

Descripción completa

Detalles Bibliográficos
Autores: Muñoz, I., Gou, P., Fulladosa, E.
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Institut de Recerca i Tecnologia Agroalimentàries (IRTA)
Repositorio:IRTA Pubpro. Open Digital Archive
OAI Identifier:oai:repositori.irta.cat:20.500.12327/683
Acceso en línea:http://hdl.handle.net/20.500.12327/683
https://doi.org/10.1016/j.foodcont.2019.06.019
Access Level:acceso abierto
Palabra clave:663/664
id ES_bf74597dfed47f3b4e91ae5f05d6201c
oai_identifier_str oai:repositori.irta.cat:20.500.12327/683
network_acronym_str ES
network_name_str España
repository_id_str
spelling Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networksMuñoz, I.Gou, P.Fulladosa, E.663/664Determination of intramuscular fat (IMF) content in dry cured meats is critical because it affects the sensory quality and consumer's acceptability. Recently, deep learning has become one of the most promising techniques in machine learning for image analysis. However, few applications in food products are found in the literature. This study presents the application of deep learning for the detection of intramuscular fat (IMF) in images of slices of dry cured ham. 8 convolutional neural networks (CNNs) have been studied and compared using segmented images (252 for training, 61 for validation and 62 for testing). The performance was compared to other simple CNNs. CNNs were able to segment IMF with an overall pixel accuracy of 0.99 and a recall and precision rates for fat near 0.82 and 0.84, respectively, using a limited number of training images. However, performance is affected by the quality of the ground truth due to the difficulty of labelling correctly pixels.info:eu-repo/semantics/acceptedVersionElsevierIndústries AlimentàriesQualitat i Tecnologia Alimentària202020202019info:eu-repo/semantics/article29application/pdfhttp://hdl.handle.net/20.500.12327/683https://doi.org/10.1016/j.foodcont.2019.06.019reponame:IRTA Pubpro. Open Digital Archiveinstname:Institut de Recerca i Tecnologia Agroalimentàries (IRTA)InglésFood ControlINIA/Programa Estatal de promoción del talento y su empleabilidad en I+D+I/RTA2013-00030-C03-01/ES/Caracterización y detección objetiva de defectos de textura en jamón curado mediante tecnologías no destructivas. Desarrollo y evaluación de medidas correctoras/Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:repositori.irta.cat:20.500.12327/6832026-06-16T08:51:17Z
dc.title.none.fl_str_mv Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
title Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
spellingShingle Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
Muñoz, I.
663/664
title_short Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
title_full Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
title_fullStr Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
title_full_unstemmed Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
title_sort Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks
dc.creator.none.fl_str_mv Muñoz, I.
Gou, P.
Fulladosa, E.
author Muñoz, I.
author_facet Muñoz, I.
Gou, P.
Fulladosa, E.
author_role author
author2 Gou, P.
Fulladosa, E.
author2_role author
author
dc.contributor.none.fl_str_mv Indústries Alimentàries
Qualitat i Tecnologia Alimentària
dc.subject.none.fl_str_mv 663/664
topic 663/664
description Determination of intramuscular fat (IMF) content in dry cured meats is critical because it affects the sensory quality and consumer's acceptability. Recently, deep learning has become one of the most promising techniques in machine learning for image analysis. However, few applications in food products are found in the literature. This study presents the application of deep learning for the detection of intramuscular fat (IMF) in images of slices of dry cured ham. 8 convolutional neural networks (CNNs) have been studied and compared using segmented images (252 for training, 61 for validation and 62 for testing). The performance was compared to other simple CNNs. CNNs were able to segment IMF with an overall pixel accuracy of 0.99 and a recall and precision rates for fat near 0.82 and 0.84, respectively, using a limited number of training images. However, performance is affected by the quality of the ground truth due to the difficulty of labelling correctly pixels.
publishDate 2019
dc.date.none.fl_str_mv 2019
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.12327/683
https://doi.org/10.1016/j.foodcont.2019.06.019
url http://hdl.handle.net/20.500.12327/683
https://doi.org/10.1016/j.foodcont.2019.06.019
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Food Control
INIA/Programa Estatal de promoción del talento y su empleabilidad en I+D+I/RTA2013-00030-C03-01/ES/Caracterización y detección objetiva de defectos de textura en jamón curado mediante tecnologías no destructivas. Desarrollo y evaluación de medidas correctoras/
dc.rights.none.fl_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 29
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:IRTA Pubpro. Open Digital Archive
instname:Institut de Recerca i Tecnologia Agroalimentàries (IRTA)
instname_str Institut de Recerca i Tecnologia Agroalimentàries (IRTA)
reponame_str IRTA Pubpro. Open Digital Archive
collection IRTA Pubpro. Open Digital Archive
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418392646057984
score 15,301629

Similares en LA Referencia