A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning

Due to the complex diversity of both fabric texture and defect, fabric defect detection is a challenge topic. However, most of existing defect detection methods can still detect only one type of fabric defects. In order to solve this problem, we propose a universal and adaptive defect detection algo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xuejuan Kang, Erhu Zhang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Defect detection sparse dictionary learning orthogonal matching pursuit K-singular value decomposition Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/d00a6e574cfb47d0a42d4626fb7e9508
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d00a6e574cfb47d0a42d4626fb7e9508
record_format	dspace
spelling	oai:doaj.org-article:d00a6e574cfb47d0a42d4626fb7e95082021-11-19T00:05:30ZA Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning2169-353610.1109/ACCESS.2020.3041849https://doaj.org/article/d00a6e574cfb47d0a42d4626fb7e95082020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9277520/https://doaj.org/toc/2169-3536Due to the complex diversity of both fabric texture and defect, fabric defect detection is a challenge topic. However, most of existing defect detection methods can still detect only one type of fabric defects. In order to solve this problem, we propose a universal and adaptive defect detection algorithm based on dictionary learning for detecting various defects of different fabric texture. Firstly, in order to make the image more balanced and improve the detection accuracy, according to the complexity of fabric texture and the degree of brightness and darkness of the background, we segment defect-free image according to a certain size to obtain the image joint matrix. In order to make the algorithm more universal, next we form a random dictionary instead of over-complete dictionary and fixed dictionary by randomly select feature columns from the image joint matrix, which can extract the most important texture and background information of fabric. Then, we use the Orthogonal Matching Pursuit algorithm to obtain the sparse representation of defect-free image. On this basis, we use the K-Singular Value Decomposition algorithm to update the dictionary iteratively to get the final dictionary. Afterward, the defective image is reconstructed with the learned dictionary to obtain the reconstruction error. Finally, the correction coefficient is obtained through reconstruction error analysis, then the corresponding adaptive threshold is used to detect and mark the location of the defects. The performance of the algorithm is evaluated on the fabric database of raw fabric, yarn-dyed fabric and patterned fabric. The experimental results show that the proposed algorithm has good universality, adaptability and a high detection success rate for different types of fabrics. Particularly, the average detection success rate of dark-red fabric and dot-patterned fabric can reach 100%, and the <italic>Precision</italic> and the <italic>Recall</italic> of defect detection evaluation index can also reach 100%.Xuejuan KangErhu ZhangIEEEarticleDefect detectionsparse dictionary learningorthogonal matching pursuitK-singular value decompositionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 221808-221830 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Defect detection sparse dictionary learning orthogonal matching pursuit K-singular value decomposition Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Defect detection sparse dictionary learning orthogonal matching pursuit K-singular value decomposition Electrical engineering. Electronics. Nuclear engineering TK1-9971 Xuejuan Kang Erhu Zhang A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
description	Due to the complex diversity of both fabric texture and defect, fabric defect detection is a challenge topic. However, most of existing defect detection methods can still detect only one type of fabric defects. In order to solve this problem, we propose a universal and adaptive defect detection algorithm based on dictionary learning for detecting various defects of different fabric texture. Firstly, in order to make the image more balanced and improve the detection accuracy, according to the complexity of fabric texture and the degree of brightness and darkness of the background, we segment defect-free image according to a certain size to obtain the image joint matrix. In order to make the algorithm more universal, next we form a random dictionary instead of over-complete dictionary and fixed dictionary by randomly select feature columns from the image joint matrix, which can extract the most important texture and background information of fabric. Then, we use the Orthogonal Matching Pursuit algorithm to obtain the sparse representation of defect-free image. On this basis, we use the K-Singular Value Decomposition algorithm to update the dictionary iteratively to get the final dictionary. Afterward, the defective image is reconstructed with the learned dictionary to obtain the reconstruction error. Finally, the correction coefficient is obtained through reconstruction error analysis, then the corresponding adaptive threshold is used to detect and mark the location of the defects. The performance of the algorithm is evaluated on the fabric database of raw fabric, yarn-dyed fabric and patterned fabric. The experimental results show that the proposed algorithm has good universality, adaptability and a high detection success rate for different types of fabrics. Particularly, the average detection success rate of dark-red fabric and dot-patterned fabric can reach 100%, and the <italic>Precision</italic> and the <italic>Recall</italic> of defect detection evaluation index can also reach 100%.
format	article
author	Xuejuan Kang Erhu Zhang
author_facet	Xuejuan Kang Erhu Zhang
author_sort	Xuejuan Kang
title	A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
title_short	A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
title_full	A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
title_fullStr	A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
title_full_unstemmed	A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning
title_sort	universal and adaptive fabric defect detection algorithm based on sparse dictionary learning
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/d00a6e574cfb47d0a42d4626fb7e9508
work_keys_str_mv	AT xuejuankang auniversalandadaptivefabricdefectdetectionalgorithmbasedonsparsedictionarylearning AT erhuzhang auniversalandadaptivefabricdefectdetectionalgorithmbasedonsparsedictionarylearning AT xuejuankang universalandadaptivefabricdefectdetectionalgorithmbasedonsparsedictionarylearning AT erhuzhang universalandadaptivefabricdefectdetectionalgorithmbasedonsparsedictionarylearning
_version_	1718420696213749760

A Universal and Adaptive Fabric Defect Detection Algorithm Based on Sparse Dictionary Learning

Ejemplares similares