Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison

Due to the huge demand for textile production in China, fabric defect detection is particularly attractive. At present, an increasing number of supervised deep-learning methods are being applied in surface defect detection. However, the annotation of datasets in industrial settings often depends on...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhengrui Peng, Xinyi Gong, Bengang Wei, Xiangyi Xu, Shixiong Meng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	fabric defect unsupervised learning computer vision deep learning Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/31b7c9e6f72c4afaab16d01da69f689b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:31b7c9e6f72c4afaab16d01da69f689b
record_format	dspace
spelling	oai:doaj.org-article:31b7c9e6f72c4afaab16d01da69f689b2021-11-11T15:39:18ZAutomatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison10.3390/electronics102126522079-9292https://doaj.org/article/31b7c9e6f72c4afaab16d01da69f689b2021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2652https://doaj.org/toc/2079-9292Due to the huge demand for textile production in China, fabric defect detection is particularly attractive. At present, an increasing number of supervised deep-learning methods are being applied in surface defect detection. However, the annotation of datasets in industrial settings often depends on professional inspectors. Moreover, the methods based on supervised learning require a lot of annotation, which consumes a great deal of time and costs. In this paper, an approach based on self-feature comparison (SFC) was employed that accurately located and segmented fabric texture images to find anomalies with unsupervised learning. The SFC architecture contained the self-feature reconstruction module and the self-feature distillation. Accurate fiber anomaly location and segmentation were generated based on these two modules. Compared with the traditional methods that operate in image space, the comparison of feature space can better locate the anomalies of fiber texture surfaces. Evaluations were performed on the three publicly available databases. The results indicated that our method performed well compared with other methods, and had excellent defect detection ability in the collected textile images. In addition, the visual results showed that our results can be used as a pixel-level candidate label.Zhengrui PengXinyi GongBengang WeiXiangyi XuShixiong MengMDPI AGarticlefabric defectunsupervised learningcomputer visiondeep learningElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2652, p 2652 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	fabric defect unsupervised learning computer vision deep learning Electronics TK7800-8360
spellingShingle	fabric defect unsupervised learning computer vision deep learning Electronics TK7800-8360 Zhengrui Peng Xinyi Gong Bengang Wei Xiangyi Xu Shixiong Meng Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
description	Due to the huge demand for textile production in China, fabric defect detection is particularly attractive. At present, an increasing number of supervised deep-learning methods are being applied in surface defect detection. However, the annotation of datasets in industrial settings often depends on professional inspectors. Moreover, the methods based on supervised learning require a lot of annotation, which consumes a great deal of time and costs. In this paper, an approach based on self-feature comparison (SFC) was employed that accurately located and segmented fabric texture images to find anomalies with unsupervised learning. The SFC architecture contained the self-feature reconstruction module and the self-feature distillation. Accurate fiber anomaly location and segmentation were generated based on these two modules. Compared with the traditional methods that operate in image space, the comparison of feature space can better locate the anomalies of fiber texture surfaces. Evaluations were performed on the three publicly available databases. The results indicated that our method performed well compared with other methods, and had excellent defect detection ability in the collected textile images. In addition, the visual results showed that our results can be used as a pixel-level candidate label.
format	article
author	Zhengrui Peng Xinyi Gong Bengang Wei Xiangyi Xu Shixiong Meng
author_facet	Zhengrui Peng Xinyi Gong Bengang Wei Xiangyi Xu Shixiong Meng
author_sort	Zhengrui Peng
title	Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
title_short	Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
title_full	Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
title_fullStr	Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
title_full_unstemmed	Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison
title_sort	automatic unsupervised fabric defect detection based on self-feature comparison
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/31b7c9e6f72c4afaab16d01da69f689b
work_keys_str_mv	AT zhengruipeng automaticunsupervisedfabricdefectdetectionbasedonselffeaturecomparison AT xinyigong automaticunsupervisedfabricdefectdetectionbasedonselffeaturecomparison AT bengangwei automaticunsupervisedfabricdefectdetectionbasedonselffeaturecomparison AT xiangyixu automaticunsupervisedfabricdefectdetectionbasedonselffeaturecomparison AT shixiongmeng automaticunsupervisedfabricdefectdetectionbasedonselffeaturecomparison
_version_	1718434657504067584

Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison

Ejemplares similares