Publicação
Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks
| Resumo: | Deep learning networks, more specifically convolutional neural networks, have shown a notable distinction when it comes to computer vision problems. Their versatility spans various domains, where they are applied for tasks such as classification and regression, contingent primarily on the availability of a representative dataset. This work explores the feasibility of employing this approach in the domain of agriculture, particularly within the context of olive growing. The objective is to enhance and facilitate cultivar identification techniques by using images of olive tree leaves. To achieve this, a comparative analysis involving ten distinct convolutional networks (VGG16, VGG19, ResNet50, ResNet152-V2, Inception V3, Inception ResNetV2, XCeption, MobileNet, MobileNetV2, EfficientNetB7) was conducted, all initiated with transfer learning as a common starting point. Also, the impact of adjusting network hyperparameters and structural elements was explored. For the training and evaluation of the networks, a dedicated dataset was created and made available, consisting of approximately 4200 images from the four most representative categories of the region. The findings of this study provide compelling evidence that the majority of the examined methods offer a robust foundation for cultivar identification, ensuring a high level of accuracy. Notably, the first nine methods consistently attain accuracy rates surpassing 95%, with the top three methods achieving an impressive 98% accuracy (ResNet50, EfficientNetB7). In practical terms, out of approximately 2016 images, 1976 were accurately classified. These results signify a substantial advancement in olive cultivar identification through computer vision techniques. |
|---|---|
| Autores principais: | Mendes, João |
| Outros Autores: | Lima, José; Costa, Lino; Rodrigues, Nuno; Pereira, Ana I. |
| Assunto: | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| Ano: | 2024 |
| País: | Portugal |
| Tipo de documento: | artigo |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | inglês |
| Origem: | Biblioteca Digital do IPB |
| _version_ | 1867173246202281984 |
|---|---|
| author | Mendes, João |
| author2 | Lima, José Costa, Lino Rodrigues, Nuno Pereira, Ana I. |
| author2_role | author author author author |
| author_facet | Mendes, João Lima, José Costa, Lino Rodrigues, Nuno Pereira, Ana I. |
| author_role | author |
| contributor_name_str_mv | Biblioteca Digital do IPB |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Mendes, João\",\"Person.identifier.orcid\":\"0000-0003-0979-8314\"},{\"Person.name\":\"Lima, José\",\"Person.identifier.orcid\":\"0000-0001-7902-1207\"},{\"Person.name\":\"Costa, Lino\"},{\"Person.name\":\"Rodrigues, Nuno\",\"Person.identifier.orcid\":\"0000-0002-9305-0976\"},{\"Person.name\":\"Pereira, Ana I.\",\"Person.identifier.orcid\":\"0000-0003-3803-2043\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | Biblioteca Digital do IPB |
| datacite.creators.creator.creatorName.fl_str_mv | Mendes, João Lima, José Costa, Lino Rodrigues, Nuno Pereira, Ana I. |
| datacite.date.Accepted.fl_str_mv | 2024-01-01T00:00:00Z |
| datacite.date.available.fl_str_mv | 2024-06-13T09:11:22Z |
| datacite.date.embargoed.fl_str_mv | 2024-06-13T09:11:22Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| datacite.titles.title.fl_str_mv | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| dc.contributor.none.fl_str_mv | Biblioteca Digital do IPB |
| dc.creator.none.fl_str_mv | Mendes, João Lima, José Costa, Lino Rodrigues, Nuno Pereira, Ana I. |
| dc.date.Accepted.fl_str_mv | 2024-01-01T00:00:00Z |
| dc.date.available.fl_str_mv | 2024-06-13T09:11:22Z |
| dc.date.embargoed.fl_str_mv | 2024-06-13T09:11:22Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://hdl.handle.net/10198/29887 |
| dc.language.none.fl_str_mv | eng |
| dc.publisher.none.fl_str_mv | Elsevier |
| dc.rights.cclincense.fl_str_mv | http://creativecommons.org/licenses/by/4.0/ |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| dc.title.fl_str_mv | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_6501 |
| description | Deep learning networks, more specifically convolutional neural networks, have shown a notable distinction when it comes to computer vision problems. Their versatility spans various domains, where they are applied for tasks such as classification and regression, contingent primarily on the availability of a representative dataset. This work explores the feasibility of employing this approach in the domain of agriculture, particularly within the context of olive growing. The objective is to enhance and facilitate cultivar identification techniques by using images of olive tree leaves. To achieve this, a comparative analysis involving ten distinct convolutional networks (VGG16, VGG19, ResNet50, ResNet152-V2, Inception V3, Inception ResNetV2, XCeption, MobileNet, MobileNetV2, EfficientNetB7) was conducted, all initiated with transfer learning as a common starting point. Also, the impact of adjusting network hyperparameters and structural elements was explored. For the training and evaluation of the networks, a dedicated dataset was created and made available, consisting of approximately 4200 images from the four most representative categories of the region. The findings of this study provide compelling evidence that the majority of the examined methods offer a robust foundation for cultivar identification, ensuring a high level of accuracy. Notably, the first nine methods consistently attain accuracy rates surpassing 95%, with the top three methods achieving an impressive 98% accuracy (ResNet50, EfficientNetB7). In practical terms, out of approximately 2016 images, 1976 were accurately classified. These results signify a substantial advancement in olive cultivar identification through computer vision techniques. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | article |
| fulltext.url.fl_str_mv | https://bibliotecadigital.ipb.pt/bitstreams/24ae8546-9808-41c7-a69c-8fe362aa70ed/download |
| funding.funder.alternateName_str_mv | FCT FCT |
| funding.funder.identifier_str_mv | http://doi.org/10.13039/501100001871 http://doi.org/10.13039/501100001871 |
| funding.funder.name_str_mv | Fundação para a Ciência e a Tecnologia Fundação para a Ciência e a Tecnologia |
| funding.name_str_mv | 6817 - DCRRNI ID 6817 - DCRRNI ID |
| id | ipb_280e6760cbb65edb4f627ba2d4f22aea |
| identifier.url.fl_str_mv | http://hdl.handle.net/10198/29887 |
| instacron_str | ipb |
| institution | Instituto Politécnico de Bragança |
| instname_str | Instituto Politécnico de Bragança |
| language | eng |
| network_acronym_str | ipb |
| network_name_str | Biblioteca Digital do IPB |
| oai_identifier_str | oai:bibliotecadigital.ipb.pt:10198/29887 |
| organization_str_mv | urn:organizationAcronym:ipb |
| person_str_mv | Mendes, João Mendes, João https://www.ciencia-id.pt/EA1F-844D-6BA9 EA1F-844D-6BA9 http://orcid.org/0000-0003-0979-8314 0000-0003-0979-8314 Lima, José Lima, José https://www.ciencia-id.pt/6016-C902-86A9 6016-C902-86A9 http://orcid.org/0000-0001-7902-1207 0000-0001-7902-1207 Costa, Lino Rodrigues, Nuno Rodrigues, Nuno https://www.ciencia-id.pt/F41D-B424-5F78 F41D-B424-5F78 http://orcid.org/0000-0002-9305-0976 0000-0002-9305-0976 Pereira, Ana I. Pereira, Ana I. https://www.ciencia-id.pt/0716-B7C2-93E4 0716-B7C2-93E4 http://orcid.org/0000-0003-3803-2043 0000-0003-3803-2043 |
| publishDate | 2024 |
| publisher.none.fl_str_mv | Elsevier |
| reponame_str | Biblioteca Digital do IPB |
| repository_id_str | urn:repositoryAcronym:ipb |
| service_str_mv | urn:repositoryAcronym:ipb |
| spelling | engElsevierpt_PTDeep learning networks, more specifically convolutional neural networks, have shown a notable distinction when it comes to computer vision problems. Their versatility spans various domains, where they are applied for tasks such as classification and regression, contingent primarily on the availability of a representative dataset. This work explores the feasibility of employing this approach in the domain of agriculture, particularly within the context of olive growing. The objective is to enhance and facilitate cultivar identification techniques by using images of olive tree leaves. To achieve this, a comparative analysis involving ten distinct convolutional networks (VGG16, VGG19, ResNet50, ResNet152-V2, Inception V3, Inception ResNetV2, XCeption, MobileNet, MobileNetV2, EfficientNetB7) was conducted, all initiated with transfer learning as a common starting point. Also, the impact of adjusting network hyperparameters and structural elements was explored. For the training and evaluation of the networks, a dedicated dataset was created and made available, consisting of approximately 4200 images from the four most representative categories of the region. The findings of this study provide compelling evidence that the majority of the examined methods offer a robust foundation for cultivar identification, ensuring a high level of accuracy. Notably, the first nine methods consistently attain accuracy rates surpassing 95%, with the top three methods achieving an impressive 98% accuracy (ResNet50, EfficientNetB7). In practical terms, out of approximately 2016 images, 1976 were accurately classified. These results signify a substantial advancement in olive cultivar identification through computer vision techniques.application/pdfpt_PTDeep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networksPersonalMendes, JoãoDSpacehttp://dspace.org/items/b5c9de22-cf9e-47b8-b7a4-26e08fb12b28DSpacehttp://dspace.org/items/b5c9de22-cf9e-47b8-b7a4-26e08fb12b28MendesJoãoCiência IDhttps://www.ciencia-id.ptEA1F-844D-6BA9ORCIDhttp://orcid.org0000-0003-0979-8314Scopus Author IDhttps://www.scopus.com57225794972PersonalLima, JoséDSpacehttp://dspace.org/items/d88c2b2a-efc2-48ef-b1fd-1145475e0055DSpacehttp://dspace.org/items/d88c2b2a-efc2-48ef-b1fd-1145475e0055LimaJoséCiência IDhttps://www.ciencia-id.pt6016-C902-86A9ORCIDhttp://orcid.org0000-0001-7902-1207Researcher IDhttps://www.researcherid.comL-3370-2014Scopus Author IDhttps://www.scopus.com55851941311Costa, LinoPersonalRodrigues, NunoDSpacehttp://dspace.org/items/00739d63-995d-4b1f-97d0-03d24c7cf0fdDSpacehttp://dspace.org/items/00739d63-995d-4b1f-97d0-03d24c7cf0fdRodriguesNunoCiência IDhttps://www.ciencia-id.ptF41D-B424-5F78ORCIDhttp://orcid.org0000-0002-9305-0976Scopus Author IDhttps://www.scopus.com55258560600PersonalPereira, Ana I.DSpacehttp://dspace.org/items/e9981d62-2a2b-4fef-b75e-c2a14b0e7846DSpacehttp://dspace.org/items/e9981d62-2a2b-4fef-b75e-c2a14b0e7846PereiraAna I.Ciência IDhttps://www.ciencia-id.pt0716-B7C2-93E4ORCIDhttp://orcid.org0000-0003-3803-2043Researcher IDhttps://www.researcherid.comF-3168-2010Scopus Author IDhttps://www.scopus.com15071961600HostingInstitutionOrganizationalBiblioteca Digital do IPBe-mailmailto:dspace@ipb.ptdspace@ipb.ptISSNIsPartOf2772-3755DOIIsPartOf10.1016/j.atech.2024.1004702024-06-13T09:11:22Z20242024-01-01T00:00:00ZHandlehttp://hdl.handle.net/10198/29887http://purl.org/coar/access_right/c_abf2open accessCNNsConvolutional neural networksCultivar identificationImage-based identificationOlive leavesPrecision agriculture1550509 bytesFundação para a Ciência e a TecnologiaResearch Centre in Digitalization and Intelligent Robotics6817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871Fundação para a Ciência e a TecnologiaResearch Centre in Digitalization and Intelligent Robotics6817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871literaturehttp://purl.org/coar/resource_type/c_6501journal article2024http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://bibliotecadigital.ipb.pt/bitstreams/24ae8546-9808-41c7-a69c-8fe362aa70ed/downloadSmart Agricultural Technology8113 |
| spellingShingle | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks Mendes, João CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| status | SINGLETON |
| subject.fl_str_mv | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| title | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| title_full | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| title_fullStr | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| title_full_unstemmed | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| title_short | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| title_sort | Deep learning networks for olive cultivar identification: a comprehensive analysis of convolutional neural networks |
| topic | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| topic_facet | CNNs Convolutional neural networks Cultivar identification Image-based identification Olive leaves Precision agriculture |
| url | http://hdl.handle.net/10198/29887 |
| visible | 1 |