Unsupervised textile defect detection using convolutional neural networks
| dc.authorid | 0000-0002-5429-7669 | |
| dc.authorid | 0000-0003-0298-0690 | |
| dc.contributor.author | Koulali, Imane | en_US |
| dc.contributor.author | Eskil, Mustafa Taner | en_US |
| dc.date.accessioned | 2025-10-06T12:48:03Z | |
| dc.date.available | 2025-10-06T12:48:03Z | |
| dc.date.issued | 2023-11-30 | |
| dc.department | Işık Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü | en_US |
| dc.department | Işık University, Faculty of Engineering and Natural Sciences, Department of Computer Engineering | en_US |
| dc.description | This 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.abstract | In 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 hyperparameter 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.sponsorship | The Support Programme for Scientific and Technological Research Projects (1001) of The Scientific and Technological Research Council of Turkey (TUBITAK) | en_US |
| dc.description.version | Preprint's Version | en_US |
| dc.identifier.citation | Koulali, I. & Eskil, M. T. (2023). Unsupervised textile defect detection using convolutional neural networks. Arxiv, 1-40. doi:https://doi.org/10.48550/arXiv.2312.00224 | en_US |
| dc.identifier.endpage | 40 | |
| dc.identifier.startpage | 1 | |
| dc.identifier.uri | https://hdl.handle.net/11729/6746 | |
| dc.identifier.uri | https://doi.org/10.48550/arXiv.2312.00224 | |
| dc.identifier.wos | PPRN:86357379 | |
| dc.identifier.wosquality | N/A | |
| dc.indekslendigikaynak | Web of Science | en_US |
| dc.indekslendigikaynak | Preprint Citation Index | en_US |
| dc.institutionauthor | Koulali, Imane | en_US |
| dc.institutionauthor | Eskil, Mustafa Taner | en_US |
| dc.institutionauthorid | 0000-0002-5429-7669 | |
| dc.institutionauthorid | 0000-0003-0298-0690 | |
| dc.language.iso | en | en_US |
| dc.publisher | Cornell Univ | en_US |
| dc.relation.ispartof | Arxiv | en_US |
| dc.relation.publicationcategory | Ön Baskı - Uluslararası - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/openAccess | en_US |
| dc.subject | Fabric defect | en_US |
| dc.subject | Textile defect | en_US |
| dc.subject | Anomaly detection | en_US |
| dc.subject | Neural network | en_US |
| dc.subject | Cross-patch | en_US |
| dc.subject | Similarity | en_US |
| dc.subject | Manhattan distance | en_US |
| dc.title | Unsupervised textile defect detection using convolutional neural networks | en_US |
| dc.type | Preprint | en_US |
| dspace.entity.type | Publication | en_US |
Dosyalar
Orijinal paket
1 - 1 / 1
Yükleniyor...
- İsim:
- Unsupervised_textile_defect_detection_using_convolutional_neural_networks.pdf
- Boyut:
- 1.82 MB
- Biçim:
- Adobe Portable Document Format
Lisans paketi
1 - 1 / 1
Küçük Resim Yok
- İsim:
- license.txt
- Boyut:
- 1.17 KB
- Biçim:
- Item-specific license agreed upon to submission
- Açıklama:
