DC FieldValueLanguage
dc.contributor.authorWang, X.-
dc.contributor.authorJiang, Guimin-
dc.contributor.authorHu, Jue-
dc.contributor.authorSfarra, Stefano-
dc.contributor.authorMostacci, Miranda-
dc.contributor.authorKouis, Dimitrios-
dc.contributor.authorYang, Dazhi-
dc.contributor.authorFernandes, Henrique-
dc.contributor.authorAvdelidis, Nicolas P.-
dc.contributor.authorMaldague, Xavier-
dc.contributor.authorGai, Yonggang-
dc.contributor.authorZhang, Hai-
dc.date.accessioned2025-03-10T08:17:02Z-
dc.date.available2025-03-10T08:17:02Z-
dc.date.issued2024-12-01-
dc.identifierscopus-85204444383-
dc.identifier.issn2050-7445-
dc.identifier.other85204444383-
dc.identifier.urihttps://uniwacris.uniwa.gr/handle/3000/3037-
dc.description.abstractIn recent years, the preservation and conservation of ancient cultural heritage necessitate the advancement of sophisticated non-destructive testing methodologies to minimize potential damage to artworks. Therefore, this study aims to develop an advanced method for detecting defects in ancient polyptychs using infrared thermography. The test subjects are two polyptych samples replicating a 14th-century artwork by Pietro Lorenzetti (1280/85–1348) with varied pigments and artificially induced defects. To address these challenges, an automatic defect detection model is proposed, integrating numerical simulation and image processing within the Faster R-CNN architecture, utilizing VGG16 as the backbone network for feature extraction. Meanwhile, the model innovatively incorporates the efficient channel attention mechanism after the feature extraction stage, which significantly improves the feature characterization performance of the model in identifying small defects in ancient polyptychs. During training, numerical simulation is utilized to augment the infrared thermal image dataset, ensuring the accuracy of subsequent experimental sample testing. Empirical results demonstrate a substantial improvement in detection performance, compared with the original Faster R-CNN model, with the average precision at the intersection over union = 0.5 increasing to 87.3% and the average precision for small objects improving to 54.8%. These results highlight the practicality and effectiveness of the model, marking a significant progress in defect detection capability, providing a strong technical guarantee for the continuous conservation of cultural heritage, and offering directions for future studies.en_US
dc.language.isoenen_US
dc.relation.ispartofHeritage Scienceen_US
dc.subjectDeep learningen_US
dc.subjectDefect detectionen_US
dc.subjectEfficient channel attentionen_US
dc.subjectFaster R-CNNen_US
dc.subjectInfrared thermographyen_US
dc.titleAutomatic defect detection in infrared thermal images of ancient polyptychs based on numerical simulation and a new efficient channel attention mechanism aided Faster R-CNN modelen_US
dc.typeArticleen_US
dc.identifier.doi10.1186/s40494-024-01441-9en_US
dc.identifier.scopus2-s2.0-85204444383-
dcterms.accessRights1en_US
dc.relation.deptDepartment of Archival, Library and Information Studiesen_US
dc.relation.facultySchool of Administrative, Economics and Social Sciencesen_US
dc.relation.volume12en_US
dc.relation.issue1en_US
dc.collaborationUniversity of West Attica (UNIWA)en_US
dc.journalsOpen Accessen_US
dc.publicationPeer Revieweden_US
dc.countryGreeceen_US
local.metadatastatusverifieden_US
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.openairetypeArticle-
item.languageiso639-1en-
item.grantfulltextnone-
crisitem.author.deptDepartment of Archival, Library and Information Studies-
crisitem.author.facultySchool of Administrative, Economics and Social Sciences-
crisitem.author.orcid0000-0002-5948-9766-
crisitem.author.parentorgSchool of Administrative, Economics and Social Sciences-
Appears in Collections:Articles / Άρθρα
CORE Recommender
Show simple item record

SCOPUSTM   
Citations

1
checked on Apr 10, 2025

Page view(s)

11
checked on Apr 11, 2025

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.