Registro sencillo

dc.rights.licenseAttribution 4.0 International*
dc.contributor.authorIntxausti Arbaiza, Eneko
dc.contributor.authorCernuda, Carlos
dc.contributor.authorZugasti, Ekhi
dc.contributor.otherSkocaj, Danijel
dc.date.accessioned2024-04-11T07:38:08Z
dc.date.available2024-04-11T07:38:08Z
dc.date.issued2024
dc.identifier.issn2076-3417en
dc.identifier.otherhttps://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=176366en
dc.identifier.urihttps://hdl.handle.net/20.500.11984/6343
dc.description.abstractIn industrial quality control, especially in the field of manufacturing defect detection, deep learning plays an increasingly critical role. However, the efficacy of these advanced models is often hindered by their need for large-scale, annotated datasets. Moreover, these datasets are mainly based on RGB images, which are very different from X-ray images. Addressing this limitation, our research proposes a methodology that incorporates domain-specific self-supervised pretraining techniques using X-ray imaging to improve defect detection capabilities in manufacturing products. We employ two pretraining approaches, SimSiam and SimMIM, to refine feature extraction from manufacturing images. The pretraining stage is carried out using an industrial dataset of 27,901 unlabeled X-ray images from a manufacturing production line. We analyze the performance of the pretraining against transfer-learning-based methods in a complex defect detection scenario using a Faster R-CNN model. We conduct evaluations on both a proprietary industrial dataset and the publicly available GDXray dataset. The findings reveal that models pretrained with domain-specific X-ray images consistently outperform those initialized with ImageNet weights. Notably, Swin Transformer models show superior results in scenarios rich in labeled data, whereas CNN backbones are more effective in limited-data environments. Moreover, we underscore the enhanced ability of the models pretrained with X-ray images in detecting critical defects, crucial for ensuring safety in industrial settings. Our study offers substantial evidence of the benefits of self-supervised learning in manufacturing defect detection, providing a solid foundation for further research and practical applications in industrial quality control.en
dc.language.isoengen
dc.publisherMDPIen
dc.rights© 2024 The Authorsen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectDefect detectionen
dc.subjectmanufacturingen
dc.subjectoptical quality controlen
dc.subjectdeep learningen
dc.subjectself-supervised learningen
dc.subjectODS 9 Industria, innovación e infraestructura
dc.titleA Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Imagesen
dcterms.accessRightshttp://purl.org/coar/access_right/c_abf2en
dcterms.sourceApplied Sciencesen
local.contributor.groupAnálisis de datos y ciberseguridades
local.description.peerreviewedtrueen
local.identifier.doihttps://doi.org/10.3390/app14072785en
local.rights.publicationfeeAPCen
local.rights.publicationfeeamount2495.58 EURen
local.contributor.otherinstitutionhttps://ror.org/05njb9z20en
local.source.detailsVol. 14. N. 7. N. art. 2785
oaire.format.mimetypeapplication/pdfen
oaire.file$DSPACE\assetstoreen
oaire.resourceTypehttp://purl.org/coar/resource_type/c_6501en
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85en
oaire.funderNameGobierno Vascoen
oaire.funderNameGobierno Vascoen
oaire.funderIdentifierhttps://ror.org/00pz2fp31 / http://data.crossref.org/fundingdata/funder/10.13039/501100003086en
oaire.funderIdentifierhttps://ror.org/00pz2fp31 / http://data.crossref.org/fundingdata/funder/10.13039/501100003086
oaire.fundingStreamIkertalde Convocatoria 2022-2025en
oaire.fundingStreamElkartek 2022en
oaire.awardNumberIT1676-22en
oaire.awardNumberKK-2022/00049en
oaire.awardTitleGrupo de sistemas inteligentes para sistemas industrialesen
oaire.awardTitleDeep learning REcommended Manufacturing Imperfection Novelty Detection (DREMIND)en
oaire.awardURISin informaciónen
oaire.awardURISin informaciónen


Ficheros en el ítem

Thumbnail
Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(es)

Registro sencillo

Attribution 4.0 International
Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution 4.0 International