CASIA OpenIR  > 复杂系统认知与决策实验室  > 水下机器人
A pixel-level deep segmentation network for automatic defect detection
Yang, Lei2; Xu, Shuai; Fan, Junfeng3; Li, En3; Liu, Yanhong1,2
Source PublicationEXPERT SYSTEMS WITH APPLICATIONS
ISSN0957-4174
2023-04-01
Volume215Pages:11
Corresponding AuthorLiu, Yanhong(liuyh@zzu.edu.cn)
AbstractDefect detection is a very important link for much manufacturing and processing applications which could be used for quality control and precise maintenance decision. However, faced with the weak-texture and low-contrast industrial environment, high-precision defect detection still faces a certain challenge due to diverse and complex of defects. Meanwhile, due to a minimal portion image pixels of defects, the pixel-level defect detection task is always against class-unbalance issue which also will affect the detection performance. Recently, with the strong automatic feature representation ability, deep learning has shown an excellent detection performance on defect identification and location. Nevertheless, it still has some demerits, such as insufficient processing of feature maps, lack of temporal modeling information, etc. To address these issues, on the basis of the encoder-decoder architecture, a pixel-level deep segmentation network is proposed for automatic defect detection to construct an end-to-end defect segmentation model. To realize effective feature representation, a residual attention network is proposed to construct the backbone network, which could also make the segmentation network better emphasize target regions. Meanwhile, to improve the network propagation ability of subtle context features, a bidirectional convolutional long short-term memory (ConvLSTM) block is introduced to optimize the skip connections to learn long-range spatial contexts. Besides, a weighted loss function is proposed for model training to address the class-unbalance issue. Combined with multiple public data sets, through qualitative and quantitative analysis, experimental results demonstrate that the proposed defect segmentation network achieves a better performance compared to other state-of-the-art segmentation methods.
KeywordDefect detection Deep convolutional neural network U-shape network ConvLSTM network
DOI10.1016/j.eswa.2022.119388
WOS KeywordINSPECTION ; RECONSTRUCTION ; SYSTEM
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[62003309] ; National Key Research & Development Project of China[2020YFB1313701] ; Science & Technology Research Project in Henan Province of China[212102210010] ; Outstanding Foreign Scientist Support Project in Henan Province of China[GZS2019008]
Funding OrganizationNational Natural Science Foundation of China ; National Key Research & Development Project of China ; Science & Technology Research Project in Henan Province of China ; Outstanding Foreign Scientist Support Project in Henan Province of China
WOS Research AreaComputer Science ; Engineering ; Operations Research & Management Science
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS IDWOS:000911042200001
PublisherPERGAMON-ELSEVIER SCIENCE LTD
Citation statistics
Cited Times:6[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/51073
Collection复杂系统认知与决策实验室_水下机器人
中国科学院工业视觉智能装备工程实验室_精密感知与控制
Corresponding AuthorLiu, Yanhong
Affiliation1.Zhengzhou Univ, Sch Elect & Informat Engn, Zhengzhou 450001, Henan, Peoples R China
2.Robot Percept & Control Engn Lab, Zhengzhou 450001, Henan, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst c, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yang, Lei,Xu, Shuai,Fan, Junfeng,et al. A pixel-level deep segmentation network for automatic defect detection[J]. EXPERT SYSTEMS WITH APPLICATIONS,2023,215:11.
APA Yang, Lei,Xu, Shuai,Fan, Junfeng,Li, En,&Liu, Yanhong.(2023).A pixel-level deep segmentation network for automatic defect detection.EXPERT SYSTEMS WITH APPLICATIONS,215,11.
MLA Yang, Lei,et al."A pixel-level deep segmentation network for automatic defect detection".EXPERT SYSTEMS WITH APPLICATIONS 215(2023):11.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Lei]'s Articles
[Xu, Shuai]'s Articles
[Fan, Junfeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Lei]'s Articles
[Xu, Shuai]'s Articles
[Fan, Junfeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Lei]'s Articles
[Xu, Shuai]'s Articles
[Fan, Junfeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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