CNN-Based Fabric Defect Detection System on Loom Fabric Inspection

Basit Öğe Kaydı
dc.authoridTalu, Muhammed Fatih/0000-0003-1166-8404
dc.authoridHanbay, Kazım/0000-0003-1374-1417
dc.authoridVarjovi, Mahdi Hatami/0000-0001-6442-7175
dc.authorwosidTalu, Muhammed Fatih/W-2834-2017
dc.authorwosidHanbay, Kazım/J-3848-2014
dc.contributor.authorTalu, Muhammed Fatih
dc.contributor.authorHanbay, Kazim
dc.contributor.authorVarjovi, Mahdi Hatami
dc.date.accessioned2024-08-04T20:53:12Z
dc.date.available2024-08-04T20:53:12Z
dc.date.issued2022
dc.departmentİnönü Üniversitesien_US
dc.description.abstractFabric defect detection is generally performed based on human visual inspection. This method is not effective and it has various difficulties such as eye delusion and labor cost. To deal with these problems, machine learning and computer vision-based intelligent systems have been developed. In this paper, a novel real-time fabric defect detection system is proposed. The proposed industrial vision system has been operated in real-time on a loom. Firstly, two fabric databases are constructed using real fabric images and new defective patch capture (DPC) algorithm. One of the main objectives in this study is to develop a CNN architecture that focuses only on fabric defect detection. One of the most unique aspects of the study is to detect defective pixel regions of fabric images with Fourier analysis on a patch-based and integrate it with deep learning Thanks to the novel developed fast Fourier transform-based DPC algorithm, defective texture areas become visible and defect-free areas are suppressed, even on complex denim fabric textures. Secondly, an appropriate convolution neural networks (CNN) model is developed. Thus the new dataset dataset is refined using negative mining method and CNN model. However, traditional feature extraction and classification approaches are also used to compare classification performances of deep models and traditional models. Experimental results show that our proposed CNN model integrated with negative mining can classify the defected images with high accuracy. Also, the proposed CNN model has been tested in real-time on a loom, and it achieves 96.5% detection accuracy. The proposed model obtains better accuracy and speed performance in terms of detection accuracy with a much smaller model size.en_US
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [Teydep-5180054]en_US
dc.description.sponsorshipThe implementation activities of this research study were carried out in the fabric production section of the CALIK DENIM [40] factory. The authors would like to thank CALIK DENIM employees. Funding was also provided by the Scientific and Technological Research Council of Turkey (TUBITAK, Teydep-5180054).en_US
dc.identifier.doi10.32710/tekstilvekonfeksiyon.1032529
dc.identifier.endpage219en_US
dc.identifier.issn1300-3356
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85142680253en_US
dc.identifier.scopusqualityQ3en_US
dc.identifier.startpage208en_US
dc.identifier.urihttps://doi.org/10.32710/tekstilvekonfeksiyon.1032529
dc.identifier.urihttps://hdl.handle.net/11616/101021
dc.identifier.volume32en_US
dc.identifier.wosWOS:000868696200003en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherE.U. Printing And Publishing Houseen_US
dc.relation.ispartofTekstil Ve Konfeksiyonen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectComputer visionen_US
dc.subjectfabric defect detectionen_US
dc.subjectCNNen_US
dc.subjectfeature extractionen_US
dc.titleCNN-Based Fabric Defect Detection System on Loom Fabric Inspectionen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu