Logo do repositório
 
Publicação

A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection

2023-09-25Artigo científico Acesso aberto
Ver registo simples
datacite.subject.fosCiências Médicas::Medicina Clínica
datacite.subject.fosCiências Naturais::Ciências da Computação e da Informação
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
datacite.subject.sdg08:Trabalho Digno e Crescimento Económico
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
datacite.subject.sdg10:Reduzir as Desigualdades
dc.contributor.authorCumbajin, Esteban
dc.contributor.authorRodrigues, Nuno
dc.contributor.authorCosta, Paulo
dc.contributor.authorMiragaia, Rolando
dc.contributor.authorFrazão, Luís
dc.contributor.authorCosta, Nuno
dc.contributor.authorFernández-Caballero, Antonio
dc.contributor.authorCarneiro, Jorge
dc.contributor.authorBuruberri, Leire H.
dc.contributor.authorPereira, António
dc.date.accessioned2026-10-19T14:56:04Z
dc.date.available2026-10-19T14:56:04Z
dc.date.issued2023-09-25
dc.description.abstractSurface defect detection with machine learning has become an important tool in industries and a large field of study for researchers or workers in recent years. It is necessary to have a simplified source of information that helps us to better focus on one type of surface. In this systematic review, we present a classification for surface defect detection based on convolutional neural networks (CNNs) focused on surface types. Findings: Out of 253 records identified, 59 primary studies were eligible. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we analyzed the structures of each study and the concepts related to defects and their types on surfaces. The presented review is mainly focused on finding a classification for the types of surfaces most used in industry (metal, building, ceramic, wood, and special). We delve into the specifics of each surface category, offering illustrative examples of their applications within both industrial and laboratory settings. Furthermore, we propose a new taxonomy of machine learning based on the obtained results and collected information. We summarized the studies and extracted the main characteristics such as type of surface, problem types, timeline, type of network, techniques, and datasets. Among the most relevant results of our analysis, we found that the metallic surface is the most used, as it is the one found in 62.71% of the studies, and the most prevalent problem type is classification, accounting for 49.15% of the total. Furthermore, we observe that transfer learning was employed in 83.05% of the studies, while data augmentation was utilized in 59.32%. Our findings also provide insights into the cameras most frequently employed, along with the strategies adopted to address illumination challenges present in certain articles and the approach to creating datasets for real-world applications. The main results presented in this review allow for a quick and efficient search of information for researchers and professionals interested in improving the results of their defect detection projects. Finally, we analyzed the trends that could open new fields of study for future research in the area of surface defect detection.eng
dc.description.sponsorshipAcknowledgments: We sincerely thank the Portuguese Fundação para a Ciência e a Tecnologia—FCT, the FITEC—Programa Interface, and the ECSEL Joint Undertaking (JU) for their valuable funding for this project. Your support has been crucial in carrying out our research and contributing to scientific and technological advancement. Funding: This work has been funded by project STC 4.0 HP—New Generation of Stoneware Tableware in Ceramic 4.0 by High-Pressure Casting Robot work cell—POCI-01-0247-FEDER-069654 and partially supported by the Portuguese Fundação para a Ciência e a Tecnologia—FCT, I.P. under the project UIDB/04524/2020, and by Portuguese national funds through FITEC—Programa Interface, with reference CIT “INOV—INESC Inovação—Financiamento Base”. This work was also partially supported by iRel40, a European cofunded innovation project that has been granted by the ECSEL Joint Undertaking (JU) (grant number 876659). The funding of the project comes from the Horizon 2020 research programme and participating countries. National funding is provided by Germany, including the Free States of Saxony and Thuringia, Austria, Belgium, Finland, France, Italy, the Netherlands, Slovakia, Spain, Sweden, and Turkey. Grant PCI2020-112001 was funded by MCIN/AEI/10.13039/501100011033 and by the European Union “NextGenerationEU”/PRTR.
dc.identifier.citationCumbajin, E.; Rodrigues, N.; Costa, P.; Miragaia, R.; Frazão, L.; Costa, N.; Fernández-Caballero, A.; Carneiro, J.; Buruberri, L.H.; Pereira, A. A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection. J. Imaging 2023, 9, 193. https://doi.org/10.3390/jimaging9100193.
dc.identifier.doi10.3390/jimaging9100193
dc.identifier.eissn2313-433X
dc.identifier.urihttp://hdl.handle.net/10400.8/17082
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI
dc.relationResearch Center in Informatics and Communications
dc.relation.hasversionhttps://www.mdpi.com/2313-433X/9/10/193
dc.relation.ispartofJournal of Imaging
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectdefect detection
dc.subjectdeep learning
dc.subjectCNN
dc.subjectindustrial surface
dc.subjectautomatic surface inspection
dc.subjectquality inspection
dc.titleA Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detectioneng
dc.typejournal article
dspace.entity.typePublication
oaire.awardNumberUIDB/04524/2020
oaire.awardTitleResearch Center in Informatics and Communications
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04524%2F2020/PT
oaire.citation.endPage29
oaire.citation.issue10
oaire.citation.startPage1
oaire.citation.titleJournal of Imaging
oaire.citation.volume9
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.affiliation.nameEng. Informática
person.familyNameCaiza Cumbajin
person.familyNameRodrigues
person.familyNameCosta
person.familyNameMiragaia
person.familyNameFrazão
person.familyNameCosta
person.familyNamePereira
person.givenNameEsteban Daniel
person.givenNameNuno Carlos Sousa
person.givenNamePaulo
person.givenNameRolando
person.givenNameLuis Alexandre Lopes
person.givenNameNuno
person.givenNameAntónio
person.identifier.ciencia-id8619-41F3-CC65
person.identifier.ciencia-idC712-E02E-0ED2
person.identifier.ciencia-idCB19-E7DA-5A7F
person.identifier.ciencia-idE215-4F0F-33EC
person.identifier.orcid0000-0002-2780-6210
person.identifier.orcid0000-0002-0953-6018
person.identifier.orcid0000-0001-5952-2709
person.identifier.orcid0000-0003-4213-9302
person.identifier.orcid0000-0003-2571-7940
person.identifier.orcid0000-0002-2353-369X
person.identifier.orcid0000-0001-5062-1241
person.identifier.ridGLS-3615-2022
person.identifier.ridM-6163-2013
person.identifier.scopus-author-id26422369700
person.identifier.scopus-author-id56890641000
person.identifier.scopus-author-id7402230199
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication472f6d9e-4dd6-4eeb-91ce-bebd14729a45
relation.isAuthorOfPublicatione4ddd3ee-555b-46e2-8663-8d1b6d9a16f8
relation.isAuthorOfPublication01277b2b-f9a2-4e19-8d18-ef065adb30f0
relation.isAuthorOfPublicationc3934650-8cbe-40cd-bb29-31c57baa49e2
relation.isAuthorOfPublicationca5eb30e-6459-4800-89ee-45f40ac7ca67
relation.isAuthorOfPublication00e2f470-c7a0-4c7e-9edd-6256f9a05c4a
relation.isAuthorOfPublication6320b167-2323-4699-bf04-9288d3f603c0
relation.isAuthorOfPublication.latestForDiscoverye4ddd3ee-555b-46e2-8663-8d1b6d9a16f8
relation.isProjectOfPublication67435020-fe0d-4b46-be85-59ee3c6138c7
relation.isProjectOfPublication.latestForDiscovery67435020-fe0d-4b46-be85-59ee3c6138c7

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection.pdf
Tamanho:
971.26 KB
Formato:
Adobe Portable Document Format
Descrição:
Surface defect detection with machine learning has become an important tool in industries and a large field of study for researchers or workers in recent years. It is necessary to have a simplified source of information that helps us to better focus on one type of surface. In this systematic review, we present a classification for surface defect detection based on convolutional neural networks (CNNs) focused on surface types. Findings: Out of 253 records identified, 59 primary studies were eligible. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we analyzed the structures of each study and the concepts related to defects and their types on surfaces. The presented review is mainly focused on finding a classification for the types of surfaces most used in industry (metal, building, ceramic, wood, and special). We delve into the specifics of each surface category, offering illustrative examples of their applications within both industrial and laboratory settings. Furthermore, we propose a new taxonomy of machine learning based on the obtained results and collected information. We summarized the studies and extracted the main characteristics such as type of surface, problem types, timeline, type of network, techniques, and datasets. Among the most relevant results of our analysis, we found that the metallic surface is the most used, as it is the one found in 62.71% of the studies, and the most prevalent problem type is classification, accounting for 49.15% of the total. Furthermore, we observe that transfer learning was employed in 83.05% of the studies, while data augmentation was utilized in 59.32%. Our findings also provide insights into the cameras most frequently employed, along with the strategies adopted to address illumination challenges present in certain articles and the approach to creating datasets for real-world applications. The main results presented in this review allow for a quick and efficient search of information for researchers and professionals interested in improving the results of their defect detection projects. Finally, we analyzed the trends that could open new fields of study for future research in the area of surface defect detection.
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.32 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

CIIC - Artigos em Revistas com Peer Review
ESTG - Artigos em revistas internacionais