SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection

doi:10.5604/01.3001.0014.3808

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	SACNN: Spatial Adversarial Convolutional Neural Network for Textile Defect Detection
	Hou, Wei 1,2; Tao, Xian 1; Ma, Wenzhi 1; Xu, De 1,2
刊名	FIBRES & TEXTILES IN EASTERN EUROPE
	2020-11-01
卷号	28 期号:6 页码:127-133
关键词	textile defect detection feature extraction feature competition CNN
ISSN号	1230-3666
DOI	10.5604/01.3001.0014.3808
通讯作者	Hou, Wei(houwei2018@ia.ac.cn)
英文摘要	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.
资助项目	National Natural Science Foundation of China[61703399] ; National Natural Science Foundation of China[62066004]
WOS研究方向	Materials Science
语种	英语
出版者	INST CHEMICAL FIBRES
WOS记录号	WOS:000591209000018
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42686]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Hou, Wei
作者单位	1.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 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.