Unsupervised textile defect detection using convolutional neural networks

Basit Öğe Kaydı
dc.authorid0000-0002-5429-7669
dc.authorid0000-0003-0298-0690
dc.contributor.authorKoulali, Imaneen_US
dc.contributor.authorEskil, Mustafa Taneren_US
dc.date.accessioned2021-11-08T16:27:34Z
dc.date.available2021-11-08T16:27:34Z
dc.date.issued2021-12
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Computer Engineeringen_US
dc.descriptionThis research is part of project "Competitive Deep Learning with Convolutional Neural Networks", grant number 118E293, supported by The Support Programme for Scientific and Technological Research Projects (1001) of The Scientific and Technological Research Council of Turkey (TUBITAK).en_US
dc.description.abstractIn this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five main steps: preprocessing, automatic pattern period extraction, patch extraction, features selection and anomaly detection. This proposed approach uses a new dynamic and heuristic method for feature selection which avoids the drawbacks of initialization of the number of filters (neurons) and their weights, and those of the backpropagation mechanism such as the vanishing gradients, which are common practice in the state-of-the-art methods. The design and training of the network are performed in a dynamic and input domain-based manner and, thus, no ad-hoc configurations are required. Before building the model, only the number of layers and the stride are defined. We do not initialize the weights randomly nor do we define the filter size or number of filters as conventionally done in CNN-based approaches. This reduces effort and time spent on hyper-parameter initialization and fine-tuning. Only one defect-free sample is required for training and no further labeled data is needed. The trained network is then used to detect anomalies on defective fabric samples. We demonstrate the effectiveness of our approach on the Patterned Fabrics benchmark dataset. Our algorithm yields reliable and competitive results (on recall, precision, accuracy and f1-measure) compared to state-of-the-art unsupervised approaches, in less time, with efficient training in a single epoch and a lower computational cost.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationKoulali, I. & Eskil, M. T. (2021). Unsupervised textile defect detection using convolutional neural networks. Applied Soft Computing, 113, 1-17. doi:10.1016/j.asoc.2021.107913en_US
dc.identifier.doi10.1016/j.asoc.2021.107913
dc.identifier.endpage17
dc.identifier.issn1568-4946
dc.identifier.issn1872-9681
dc.identifier.scopus2-s2.0-85116036671
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/11729/3279
dc.identifier.urihttp://dx.doi.org/10.1016/j.asoc.2021.107913
dc.identifier.volume113
dc.identifier.wosWOS:000722555800009
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorKoulali, Imaneen_US
dc.institutionauthorEskil, Mustafa Taneren_US
dc.institutionauthorid0000-0002-5429-7669
dc.institutionauthorid0000-0003-0298-0690
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherElsevier Ltden_US
dc.relation.ispartofApplied Soft Computingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAnomaly detectionen_US
dc.subjectComputational efficiencyen_US
dc.subjectConvolutionen_US
dc.subjectConvolutional neural networksen_US
dc.subjectCross-patch similarityen_US
dc.subjectDefect detectionen_US
dc.subjectExtractionen_US
dc.subjectFabric defecten_US
dc.subjectFeature extractionen_US
dc.subjectFeatures selectionen_US
dc.subjectHeuristic methodsen_US
dc.subjectManhattan distanceen_US
dc.subjectNeural networken_US
dc.subjectPattern perioden_US
dc.subjectTextile defecten_US
dc.subjectTextilesen_US
dc.titleUnsupervised textile defect detection using convolutional neural networksen_US
dc.typeArticleen_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
11729-3279.pdf
Boyut:
5.57 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu