Repository logo
 
Publication

Synthetic image generation for effective deep learning model training for ceramic industry applications

2025-03Journal article Open access
Simple item page
datacite.subject.fosEngenharia e Tecnologia
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
dc.contributor.authorGaspar, Fábio
dc.contributor.authorDaniel Carreira
dc.contributor.authorRodrigues, Nuno
dc.contributor.authorMiragaia, Rolando
dc.contributor.authorRibeiro, José
dc.contributor.authorCosta, Paulo
dc.contributor.authorPereira, António
dc.date.accessioned2025-07-21T13:41:58Z
dc.date.available2025-07-21T13:41:58Z
dc.date.issued2025-03
dc.descriptionArticle number - 110019
dc.description.abstractIn the rapidly evolving field of machine learning engineering, access to large, high-quality, and well-balanced labeled datasets is indispensable for accurate product classification. This necessity holds particular significance in sectors such as the ceramics industry, in which effective production line activities are paramount and deep learning classification mechanisms are particularly relevant for streamlining processes; but real-world image samples are scarce and difficult to obtain, hindering dataset building and consequently model training and deployment. This paper presents a novel approach for dataset building in the context of the ceramic industry, which involves employing synthetic images for building or complementing datasets for image classification problems. The proposed methodology was implemented in CeramicFlow, an innovative computer graphics rendering pipeline designed to create synthetic images by employing computer-aided design models of ceramic objects and incorporating domain randomization techniques. As a result, a fully synthetic image dataset named Synthetic CeramicNet was created and validated in real-world ceramic classification problems. The results demonstrate that synthetic images provide an adequate basis for datasets and can significantly reduce reliance on real-world data when developing deep learning approaches for image classification problems in the ceramic industry. Furthermore, the proposed approach can potentially be applied to other industrial fields.eng
dc.description.sponsorship• This work was supported by national funds through the PortugueseFoundation for Science and Technology (FCT), I.P., under the project UIDB/04524/2020. • STC 4.0 HP - New Generation of Stoneware Tableware in Ceramic4.0 by High Pressure Casting Robot work cell, Referência: No69654,I&DT Empresarial (Copromoção, Parcerias Internacionais). • I DECOR - I & D sistema avançado de aplicação de decorações em tableware – Controlo de Qualidade (RefaCandidatura: C679416409-00009762, RefaSubmissão: T679994395-00003392).
dc.identifier.citationFábio Gaspar, Daniel Carreira, Nuno Rodrigues, Rolando Miragaia, José Ribeiro, Paulo Costa, António Pereira, Synthetic image generation for effective deep learning model training for ceramic industry applications, Engineering Applications of Artificial Intelligence, Volume 143, 2025, 110019, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2025.110019
dc.identifier.doi10.1016/j.engappai.2025.110019
dc.identifier.issn0952-1976
dc.identifier.urihttp://hdl.handle.net/10400.8/13731
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier
dc.relationResearch Center in Informatics and Communications
dc.relation.hasversionhttps://www.sciencedirect.com/science/article/pii/S0952197625000193
dc.relation.ispartofEngineering Applications of Artificial Intelligence
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectCeramic industry
dc.subjectComputer vision
dc.subjectDeep learning
dc.subjectImage classification
dc.subjectSynthetic data
dc.titleSynthetic image generation for effective deep learning model training for ceramic industry applicationseng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleResearch Center in Informatics and Communications
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04524%2F2020/PT
oaire.citation.titleEngineering Applications of Artificial Intelligence
oaire.citation.volume143
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameGaspar
person.familyNameSOARES CARREIRA
person.familyNameM. M. Rodrigues
person.familyNameMiragaia
person.familyNameRibeiro
person.familyNameCosta
person.familyNamePereira
person.givenNameFábio
person.givenNameDANIEL
person.givenNameNuno
person.givenNameRolando
person.givenNameJosé
person.givenNamePaulo
person.givenNameAntónio
person.identifier.ciencia-idD817-2BA9-4F48
person.identifier.ciencia-id4E10-91E1-17D2
person.identifier.ciencia-idC712-E02E-0ED2
person.identifier.ciencia-idE215-4F0F-33EC
person.identifier.orcid0000-0001-5589-9904
person.identifier.orcid0000-0001-8785-6001
person.identifier.orcid0000-0001-9536-1017
person.identifier.orcid0000-0003-4213-9302
person.identifier.orcid0000-0001-9278-9296
person.identifier.orcid0000-0001-5952-2709
person.identifier.orcid0000-0001-5062-1241
person.identifier.ridGLS-3615-2022
person.identifier.ridM-6163-2013
person.identifier.scopus-author-id7006052345
person.identifier.scopus-author-id26422369700
person.identifier.scopus-author-id7402230199
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication4f194e05-7be3-4348-aeed-14ac309f4c7f
relation.isAuthorOfPublication989f2933-0fc5-490b-8e7e-280ce7f37b52
relation.isAuthorOfPublicationb4ebe652-7f0e-4e67-adb0-d5ea29fc9e69
relation.isAuthorOfPublicationc3934650-8cbe-40cd-bb29-31c57baa49e2
relation.isAuthorOfPublication281c8f65-d223-4c20-94ca-21187745ea2d
relation.isAuthorOfPublication01277b2b-f9a2-4e19-8d18-ef065adb30f0
relation.isAuthorOfPublication6320b167-2323-4699-bf04-9288d3f603c0
relation.isAuthorOfPublication.latestForDiscovery4f194e05-7be3-4348-aeed-14ac309f4c7f
relation.isProjectOfPublication67435020-fe0d-4b46-be85-59ee3c6138c7
relation.isProjectOfPublication.latestForDiscovery67435020-fe0d-4b46-be85-59ee3c6138c7

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0952197625000193-main.pdf
Size:
3.33 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ESTG - Artigos em revistas internacionais
INESCC-DL - Artigos em Revistas Internacionais