Mask-Guided Generation Method for Industrial Defect Images with Non-uniform Structures

doi:10.3390/machines10121239

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Mask-Guided Generation Method for Industrial Defect Images with Non-uniform Structures
	Wei, Jing 1,2; Zhang, Zhengtao1,2,3 ; Shen, Fei1,2,3 ; Lv, Chengkan1,2,3
发表期刊	MACHINES
	2022-12-01
卷号	10 期号:12 页码:17
通讯作者	Lv, Chengkan(chengkan.lv@ia.ac.cn)
摘要	Defect generation is a crucial method for solving data problems in industrial defect detection. However, the current defect generation methods suffer from the problems of background information loss, insufficient consideration of complex defects, and lack of accurate annotations, which limits their application in defect segmentation tasks. To tackle these problems, we proposed a mask-guided background-preserving defect generation method, MDGAN (mask-guided defect generation adversarial networks). First, to preserve the normal background and provide accurate annotations for the generated defect samples, we proposed a background replacement module (BRM), to add real background information to the generator and guide the generator to only focus on the generation of defect content in specified regions. Second, to guarantee the quality of the generated complex texture defects, we proposed a double discrimination module (DDM), to assist the discriminator in measuring the realism of the input image and distinguishing whether or not the defects were distributed at specified locations. The experimental results on metal, fabric, and plastic products showed that MDGAN could generate diversified and high-quality defect samples, demonstrating an improvement in detection over the traditional augmented samples. In addition, MDGAN can transfer defects between datasets with similar defect contents, thus achieving zero-shot defect detection.
关键词	industrial manufacturing deep learning data augmentation defect generation defect detection
DOI	10.3390/machines10121239
收录类别	SCI
语种	英语
资助项目	Youth Innovation Promotion Association, CAS ; [2020139]
项目资助者	Youth Innovation Promotion Association, CAS
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic ; Engineering, Mechanical
WOS记录号	WOS:000900844200001
出版者	MDPI
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51315
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Lv, Chengkan
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.CASI Vis Technol Co Ltd, Luoyang 471000, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wei, Jing,Zhang, Zhengtao,Shen, Fei,et al. Mask-Guided Generation Method for Industrial Defect Images with Non-uniform Structures[J]. MACHINES,2022,10(12):17.
APA	Wei, Jing,Zhang, Zhengtao,Shen, Fei,&Lv, Chengkan.(2022).Mask-Guided Generation Method for Industrial Defect Images with Non-uniform Structures.MACHINES,10(12),17.
MLA	Wei, Jing,et al."Mask-Guided Generation Method for Industrial Defect Images with Non-uniform Structures".MACHINES 10.12(2022):17.