Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.livsci.2022.105152 http://hdl.handle.net/11449/249028 |
Resumo: | The objective of this study was to investigate the potential of creating a pipeline to classify the marbling score obtained from ribeye area (REA) images using computer vision and machine learning methods. Our database consisted of images and measurements (N = 2,446) from the transversal cut between the 12th and 13th ribs of the Longissimus dorsi muscle from carcasses of a beef cattle population (Bos taurus). Each sample was previously labeled by the industry using a low, medium or high marbling score. The prediction accuracies of two tree-based Machine Learning (ML) algorithms (Decision Tree - DT and Random Forest - RF) were compared, as well as different measures for extracting features from the REA images, which were used as input for the ML algorithms. In order to extract features based on detectable color patterns and textures contained in smaller parts of the grayscale image, we proposed the application of the local binary pattern (LBP) method prior to the adoption of ML methods. Mean classification accuracies for the test set ranged from 45.78% to 91.25% for different test scenarios. The results were mostly impacted by the feature extraction metrics, ML methods, potential subjectivity during the classification process by the industry, and the number of classes evaluated together. The best prediction accuracy results were achieved after performing the cross-validation (20% in each balanced group, 5 folds, and 10 repetitions), considering solely the extreme groups (low and high marbling scores) and pre-selecting from each group the 400 most visually representative samples. The RF algorithm outperformed the DT for most scenarios. After increasing the number of images to 580 samples for the same two groups, the highest testing accuracies were reduced to 83.05% for RF and 75.58% for DT. Such a decrease in the classification accuracies may be associated with the addition of erroneously classified images, due to the subjective nature of the industry evaluation. In conclusion, our preliminary studies showed the LBP method as a powerful feature extraction strategy considering a scenario where the labels were well defined. Our results revealed high accuracies for the classification of marbling extremes, but there is an evident need to improve the understanding of the biological and visual aspects that led to a sharp drop in classification accuracy after the insertion of the intermediate groups of marbling. In addition, the authors highlight the importance of an accurate labeling process for achieving better classification accuracy when applying supervised classification methods. |
id |
UNSP_57a0c3fc3bc83e9b27531b5598b6ff74 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/249028 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithmsImage featuresLocal binary patternMachine learningMarbling scoreRibeye areaThe objective of this study was to investigate the potential of creating a pipeline to classify the marbling score obtained from ribeye area (REA) images using computer vision and machine learning methods. Our database consisted of images and measurements (N = 2,446) from the transversal cut between the 12th and 13th ribs of the Longissimus dorsi muscle from carcasses of a beef cattle population (Bos taurus). Each sample was previously labeled by the industry using a low, medium or high marbling score. The prediction accuracies of two tree-based Machine Learning (ML) algorithms (Decision Tree - DT and Random Forest - RF) were compared, as well as different measures for extracting features from the REA images, which were used as input for the ML algorithms. In order to extract features based on detectable color patterns and textures contained in smaller parts of the grayscale image, we proposed the application of the local binary pattern (LBP) method prior to the adoption of ML methods. Mean classification accuracies for the test set ranged from 45.78% to 91.25% for different test scenarios. The results were mostly impacted by the feature extraction metrics, ML methods, potential subjectivity during the classification process by the industry, and the number of classes evaluated together. The best prediction accuracy results were achieved after performing the cross-validation (20% in each balanced group, 5 folds, and 10 repetitions), considering solely the extreme groups (low and high marbling scores) and pre-selecting from each group the 400 most visually representative samples. The RF algorithm outperformed the DT for most scenarios. After increasing the number of images to 580 samples for the same two groups, the highest testing accuracies were reduced to 83.05% for RF and 75.58% for DT. Such a decrease in the classification accuracies may be associated with the addition of erroneously classified images, due to the subjective nature of the industry evaluation. In conclusion, our preliminary studies showed the LBP method as a powerful feature extraction strategy considering a scenario where the labels were well defined. Our results revealed high accuracies for the classification of marbling extremes, but there is an evident need to improve the understanding of the biological and visual aspects that led to a sharp drop in classification accuracy after the insertion of the intermediate groups of marbling. In addition, the authors highlight the importance of an accurate labeling process for achieving better classification accuracy when applying supervised classification methods.Department of Nutrition and Animal Production (VNP) School of Veterinary Medicine and Animal Science University of São Paulo, SPCentre for Genetic Improvement of Livestock (CGIL) Departament of Animal Biosciences University of GuelphAgSightsLivestock Research Innovation CorporationDepartment of Animal & Dairy Sciences University of Wisconsin-MadisonAnimal Science Department School of Agricultural and Veterinarian Sciences São Paulo State University, SPDepartment of Basic Science The Faculty of Animal Science and Food Engineering University of São Paulo, SPAnimal Science Department School of Agricultural and Veterinarian Sciences São Paulo State University, SPUniversidade de São Paulo (USP)University of GuelphAgSightsLivestock Research Innovation CorporationUniversity of Wisconsin-MadisonUniversidade Estadual Paulista (UNESP)Pinto, Diógenes LodiSelli, AlanaTulpan, DanAndrietta, Lucas TassoniGarbossa, Pollyana Leite MatioliVoort, Gordon VanderMunro, JasperMcMorris, MikeAlves, Anderson Antonio CarvalhoCarvalheiro, Roberto [UNESP]Poleti, Mirele DaianaBalieiro, Júlio Cesar de CarvalhoVentura, Ricardo Vieira2023-07-29T14:00:23Z2023-07-29T14:00:23Z2023-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.livsci.2022.105152Livestock Science, v. 267.1871-1413http://hdl.handle.net/11449/24902810.1016/j.livsci.2022.1051522-s2.0-85145974639Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengLivestock Scienceinfo:eu-repo/semantics/openAccess2024-09-09T13:02:03Zoai:repositorio.unesp.br:11449/249028Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462024-09-09T13:02:03Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
title |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
spellingShingle |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms Pinto, Diógenes Lodi Image features Local binary pattern Machine learning Marbling score Ribeye area |
title_short |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
title_full |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
title_fullStr |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
title_full_unstemmed |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
title_sort |
Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms |
author |
Pinto, Diógenes Lodi |
author_facet |
Pinto, Diógenes Lodi Selli, Alana Tulpan, Dan Andrietta, Lucas Tassoni Garbossa, Pollyana Leite Matioli Voort, Gordon Vander Munro, Jasper McMorris, Mike Alves, Anderson Antonio Carvalho Carvalheiro, Roberto [UNESP] Poleti, Mirele Daiana Balieiro, Júlio Cesar de Carvalho Ventura, Ricardo Vieira |
author_role |
author |
author2 |
Selli, Alana Tulpan, Dan Andrietta, Lucas Tassoni Garbossa, Pollyana Leite Matioli Voort, Gordon Vander Munro, Jasper McMorris, Mike Alves, Anderson Antonio Carvalho Carvalheiro, Roberto [UNESP] Poleti, Mirele Daiana Balieiro, Júlio Cesar de Carvalho Ventura, Ricardo Vieira |
author2_role |
author author author author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade de São Paulo (USP) University of Guelph AgSights Livestock Research Innovation Corporation University of Wisconsin-Madison Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Pinto, Diógenes Lodi Selli, Alana Tulpan, Dan Andrietta, Lucas Tassoni Garbossa, Pollyana Leite Matioli Voort, Gordon Vander Munro, Jasper McMorris, Mike Alves, Anderson Antonio Carvalho Carvalheiro, Roberto [UNESP] Poleti, Mirele Daiana Balieiro, Júlio Cesar de Carvalho Ventura, Ricardo Vieira |
dc.subject.por.fl_str_mv |
Image features Local binary pattern Machine learning Marbling score Ribeye area |
topic |
Image features Local binary pattern Machine learning Marbling score Ribeye area |
description |
The objective of this study was to investigate the potential of creating a pipeline to classify the marbling score obtained from ribeye area (REA) images using computer vision and machine learning methods. Our database consisted of images and measurements (N = 2,446) from the transversal cut between the 12th and 13th ribs of the Longissimus dorsi muscle from carcasses of a beef cattle population (Bos taurus). Each sample was previously labeled by the industry using a low, medium or high marbling score. The prediction accuracies of two tree-based Machine Learning (ML) algorithms (Decision Tree - DT and Random Forest - RF) were compared, as well as different measures for extracting features from the REA images, which were used as input for the ML algorithms. In order to extract features based on detectable color patterns and textures contained in smaller parts of the grayscale image, we proposed the application of the local binary pattern (LBP) method prior to the adoption of ML methods. Mean classification accuracies for the test set ranged from 45.78% to 91.25% for different test scenarios. The results were mostly impacted by the feature extraction metrics, ML methods, potential subjectivity during the classification process by the industry, and the number of classes evaluated together. The best prediction accuracy results were achieved after performing the cross-validation (20% in each balanced group, 5 folds, and 10 repetitions), considering solely the extreme groups (low and high marbling scores) and pre-selecting from each group the 400 most visually representative samples. The RF algorithm outperformed the DT for most scenarios. After increasing the number of images to 580 samples for the same two groups, the highest testing accuracies were reduced to 83.05% for RF and 75.58% for DT. Such a decrease in the classification accuracies may be associated with the addition of erroneously classified images, due to the subjective nature of the industry evaluation. In conclusion, our preliminary studies showed the LBP method as a powerful feature extraction strategy considering a scenario where the labels were well defined. Our results revealed high accuracies for the classification of marbling extremes, but there is an evident need to improve the understanding of the biological and visual aspects that led to a sharp drop in classification accuracy after the insertion of the intermediate groups of marbling. In addition, the authors highlight the importance of an accurate labeling process for achieving better classification accuracy when applying supervised classification methods. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T14:00:23Z 2023-07-29T14:00:23Z 2023-01-01 |
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/10.1016/j.livsci.2022.105152 Livestock Science, v. 267. 1871-1413 http://hdl.handle.net/11449/249028 10.1016/j.livsci.2022.105152 2-s2.0-85145974639 |
url |
http://dx.doi.org/10.1016/j.livsci.2022.105152 http://hdl.handle.net/11449/249028 |
identifier_str_mv |
Livestock Science, v. 267. 1871-1413 10.1016/j.livsci.2022.105152 2-s2.0-85145974639 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Livestock Science |
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 |
repositoriounesp@unesp.br |
_version_ |
1810021351914733568 |