Colour‐patterned fabric defect detection based on an unsupervised multi‐scale U‐shaped denoising convolutional autoencoder model

This study proposes an unsupervised, learning‐based, reconstructed scheme and a residual analysis‐based defect detection model for colour‐patterned fabric defect detection problems in the clothing process industry. It solves the challenging problems of existing supervised fabric defect detection met...

Full description

Saved in:
Bibliographic Details
Published in:Coloration technology Vol. 138; no. 5; pp. 522 - 537
Main Authors: Zhang, Hongwei, Liu, Shuting, Tan, Quanlu, Lu, Shuai, Yao, Le, Ge, Zhiqiang
Format: Journal Article
Language:English
Published: Bradford Wiley Subscription Services, Inc 01.10.2022
Subjects:
Color
Defects
Image reconstruction
Noise reduction
ISSN:1472-3581, 1478-4408
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study proposes an unsupervised, learning‐based, reconstructed scheme and a residual analysis‐based defect detection model for colour‐patterned fabric defect detection problems in the clothing process industry. It solves the challenging problems of existing supervised fabric defect detection methods, such as high costs in manually labelling samples and designing features, unstable generalisation ability and scarcity of defective samples. First, for a specific texture, the training set was constructed by collecting easily accessible defect‐free colour‐patterned fabric images. Second, a multi‐scale U‐shaped denoising convolutional autoencoder was modelled using defect‐free samples, which can reconstruct the newly tested colour‐patterned fabric images automatically. Subsequently, a residual map between the original image and corresponding reconstructed image was calculated. Finally, the defective areas were detected and accurately localised by further opening operations. The experimental results indicated that the proposed method is valid and robust for detecting defects in various colour‐patterned fabrics. Moreover, with the YDFID‐1 dataset, compared with other models, the intersection over union index of the model proposed in the current paper was improved by at least 3.95%.
Bibliography:Funding information
the Graduate Scientific Innovation Fund for Xi'an Polytechnic University under Grant chx2021015; the Key R&D Plan of Shaanxi Province under Grant 2019ZDLGY01‐08; the National Natural Science Foundation of China under Grant 61803292; the Natural Science Foundation of Shaanxi Province under Grant 2019JM‐263; the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (No. ICT2021B04); Xi'an Polytechnic University; Innovation Fund; Natural Science Foundation of Shaanxi Province; Zhejiang University; State Key Laboratory of Industrial Control Technology; National Natural Science Foundation of China
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1472-3581
1478-4408
DOI:10.1111/cote.12609