A Nested Autoencoder Approach to Automated Defect Inspection on Textured Surfaces

Basit Öğe Kaydı
dc.authorid0000-0001-7553-6887en_US
dc.authorscopusid23469630000en_US
dc.authorwosidAAZ-6561-2020en_US
dc.contributor.authorÖz, Muhammed Ali Nur
dc.contributor.authorKaymakçı, Özgur Turay
dc.contributor.authorMercimek, Muharrem
dc.date.accessioned2023-06-19T12:44:36Z
dc.date.available2023-06-19T12:44:36Z
dc.date.issued2021en_US
dc.departmentFakülteler, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü
dc.description.abstractIn recent years, there has been a highly competitive pressure on industrial production. To keep ahead of the competition, emerging technologies must be developed and incorporated. Automated visual inspection systems, which improve the overall mass production quantity and quality in lines, are crucial. The modifications of the inspection system involve excessive time and money costs. Therefore, these systems should be flexible in terms of fulfilling the changing requirements of high capacity production support. A coherent defect detection model as a primary application to be used in a real-time intelligent visual surface inspection system is proposed in this paper. The method utilizes a new approach consisting of nested autoencoders trained with defect-free and defect injected samples to detect defects. Making use of two nested autoencoders, the proposed approach shows great performance in eliminating defects. The first autoencoder is used essentially for feature extraction and reconstructing the image from these features. The second one is employed to identify and fix defects in the feature code. Defects are detected by thresholding the difference between decoded feature code outputs of the first and the second autoencoder. The proposed model has a 96% detection rate and a relatively good segmentation performance while being able to inspect fabrics driven at high speeds.en_US
dc.identifier.citationÖz, M. A. N., Kaymakçı, O. T., & Mercimek, M. (2021). A nested autoencoder approach to automated defect inspection on textured surfaces. International Journal of Applied Mathematics and Computer Science, 31(3), 515-523. doi:10.34768/amcs-2021-0035en_US
dc.identifier.doi10.34768/amcs-2021-0035
dc.identifier.endpage523en_US
dc.identifier.issn1641-876X
dc.identifier.issn2083-8492
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85117117912
dc.identifier.startpage515en_US
dc.identifier.urihttps://doi.org/10.34768/amcs-2021-0035
dc.identifier.urihttps://hdl.handle.net/20.500.12428/4324
dc.identifier.volume31en_US
dc.identifier.wosWOS:000709868600011
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorKaymakçı, Özgur Turay
dc.language.isoen
dc.publisherSciendoen_US
dc.relation.ispartofInternational Journal of Applied Mathematics and Computer Scienceen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.relation.tubitakinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/118E607
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectAutoencodersen_US
dc.subjectAutomatic visual inspectionen_US
dc.subjectDeep learningen_US
dc.subjectDefect detectionen_US
dc.titleA Nested Autoencoder Approach to Automated Defect Inspection on Textured Surfaces
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Ozgur_Turay_Kaymakci_Makale.pdf
Boyut:
1.61 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Araştırma Makalesi
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Elektronik Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu