SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection
Hou, Wei1,2; Tao, Xian2; Ma, Wenzhi2; Xu, De1,2
Source PublicationFIBRES & TEXTILES IN EASTERN EUROPE
ISSN1230-3666
2020-11-01
Volume28Issue:6Pages:127-133
Abstract

Constructing textile defect detection systems is significant for quality control in industrial production, but it is costly and laborious to label sufficient detailed samples. This paper proposes a model called 'spatial adversarial convolutional neural network' which tries to solve the problem above by only using the image-level label. It consists of two parts: a feature extractor and feature competition. Firstly, a string of convolutional blocks is used as a feature extractor. After feature extraction, a maximum greedy feature competition is taken amongfeatures in thefeature layer. The feature competition mechanism can lead the network to converge to the defect location. To evaluate this mechanism, experiments were carried on two datasets. As the training time increases, the model can spontaneously focus on the actual defective location, and is robust towards an unbalanced sample. The classification accuracy of the two datasets can reach more than 98%, and is comparable with the method of labelling samples in detail. Detection results show that defect location from the model is more compact and accurate than in the Grad-CAM method. Experiments show that our model has potential usage in defect detection in an industrial environment.

Keywordtextile defect detection feature extraction feature competition CNN
DOI10.5604/01.3001.0014.3808
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61703399] ; National Natural Science Foundation of China[62066004]
Funding OrganizationNational Natural Science Foundation of China
WOS Research AreaMaterials Science
WOS SubjectMaterials Science, Textiles
WOS IDWOS:000591209000018
PublisherINST CHEMICAL FIBRES
Sub direction classification人工智能+制造
planning direction of the national heavy laboratory先进智能应用与转化
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/42687
Collection中科院工业视觉智能装备工程实验室_精密感知与控制
Corresponding AuthorHou, Wei
Affiliation1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
2.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Hou, Wei,Tao, Xian,Ma, Wenzhi,et al. SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection[J]. FIBRES & TEXTILES IN EASTERN EUROPE,2020,28(6):127-133.
APA Hou, Wei,Tao, Xian,Ma, Wenzhi,&Xu, De.(2020).SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection.FIBRES & TEXTILES IN EASTERN EUROPE,28(6),127-133.
MLA Hou, Wei,et al."SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection".FIBRES & TEXTILES IN EASTERN EUROPE 28.6(2020):127-133.
Files in This Item: Download All
File Name/Size DocType Version Access License
18_Hou_SACNN_2020_6.(3209KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hou, Wei]'s Articles
[Tao, Xian]'s Articles
[Ma, Wenzhi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hou, Wei]'s Articles
[Tao, Xian]'s Articles
[Ma, Wenzhi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hou, Wei]'s Articles
[Tao, Xian]'s Articles
[Ma, Wenzhi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 18_Hou_SACNN_2020_6.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.