A Few-shot Learning Method for the Defect Inspection of Lithium Battery Sealing Nails
Pages 983 - 989
Abstract
Vision-based industrial surface defect detection utilizing computer vision technologies to analyze defects in the appearance of industrial products has become popular in intelligent manufacturing. It makes inspectors move away from inefficient and labor-consuming traditional inspection methods. In this field, sealing nails play a vital role in the power battery of vehicles, and the industrial piece needs strict quality inspection according to its visual appearance before application. However, many difficulties exist, such as the lack of defect samples, low visibility of defects, and irregular shapes in the defect detection of industrial sealing nails. In this paper, we first re-labeled all non-normal areas based on the geometric contour features of the defects and made a practical classification. Second, obtain multi-dimensional image information by the polarization imaging technique; thus, it can effectively cope with low visibility. Third, proposing a new context-based Copy-Paste augmentation approach that can effectively expand the sealing nail dataset and improve the segmentation accuracy. Several experimental results have proven our methods’ accuracy and feasibility in segmentation detection models. For example, the mean pixel accuracy(mPA) criteria enhanced by about 14.9% compared with traditional methods.
References
[1]
Young Hoon Cho, Jinwuk Seok, and Jeong-Si Kim. 2021. DARS: Data Augmentation using Refined Segmentation on Computer Vision Tasks. In Proceedings of the 12th International Conference on ICT Convergence (ICTC) (Jeju Island, South Korea) (ICTC ’21). IEEE, 348–350. https://doi.org/10.1109/ICTC52510.2021.9620807
[2]
DerSIEG. 2022. Welding quality inspection of sealing nail of new energy battery. DerSIEG (19 Feb. 2022). https://www.dersieg.net/dersieg/vip_doc/21616238.html
[3]
Nikita Dvornik, Julien Mairal, and Cordelia Schmid. 2018. Modeling Visual Context Is Key to Augmenting Object Detection Datasets. In Computer Vision - ECCV 2018(Lecture Notes in Computer Science, Vol. 11216). Springer, 375–391. https://doi.org/10.1007/978-3-030-01258-8_23
[4]
Debidatta Dwibedi, Ishan Misra, and Martial Hebert. 2017. Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection. In 2017 IEEE International Conference on Computer Vision (ICCV). IEEE, 1310–1319. https://doi.org/10.1109/ICCV.2017.146
[5]
Simen Keiland Fondevik, Annette Stahl, Aksel Andreas Transeth, and Ole Oystein Knudsen. 2020. Image Segmentation of Corrosion Damages in Industrial Inspections. In 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI)(Proceedings-International Conference on Tools With Artificial Intelligence), M Alamaniotis and S Pan (Eds.). IEEE; IEEE Comp Soc; Biol & Artificial Intelligence Fdn, 787–792. https://doi.org/10.1109/ICTAI50040.2020.00125 32nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI), ELECTR NETWORK, NOV 09-11, 2020.
[6]
Georgios Georgakis, Arsalan Mousavian, Alexander C. Berg, and Jana Kočecká. 2017. Synthesizing Training Data for Object Detection in Indoor Scenes. In Proceedings of Robotics: Science and Systems. https://doi.org/10.15607/rss.2017.xiii.043
[7]
Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D. Cubuk, Quoc Le, V, and Barret Zoph. 2021. Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation. In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(IEEE Conference on Computer Vision and Pattern Recognition). IEEE; IEEE Comp Soc; CVF, 2917–2927. https://doi.org/10.1109/CVPR46437.2021.00294 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, JUN 19-25, 2021.
[8]
Huang Guangjun, Lie Zhihao, Wang Xingzheng, Zhong Xiaopin, and Deng Yuanlong. 2022. Inspection of Slight Aesthetic Defects in a Polarizing Film via Polarization Imaging. Journal of Electronics & Information Technology 44, 5 (MAY 2022), 1636–1642. https://doi.org/10.11999/JEIT210870
[9]
Ankush Gupta, Andrea Vedaldi, and Andrew Zisserman. 2016. Synthetic Data for Text Localisation in Natural Images. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society and Computer Vision Foundation, 2315–2324. https://doi.org/10.1109/CVPR.2016.254
[10]
Luo Haibo, Cao Junfeng, Gai Xingqin, and Ding Qinghai. 2022. Industrial Vision Based on Polarization Imaging and Its Key Technologies. Laser & Optoelectronics Progress 59, 14 (JUL 2022), 44–52. Issue 14. https://doi.org/10.3788/LOP202259.1415003
[11]
Hanswell. 2022. Welding quality inspection of battery sealing nails. Gongkong (3 Aug. 2022). http://www.gongkong.com/article/202208/101051.html
[12]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2016-December, 770 – 778. http://dx.doi.org/10.1109/CVPR.2016.90 Classification tasks;Gain accuracy;Learning frameworks;Lower complexity;Residual functions;Test sets;Visual recognition;.
[13]
ZHANG Yi HUANG Cong, NONG Yingxiong. 2022. Intelligent Anomaly Detection for Industrial Product Quality Inspection Based on Gaussian Restricted Boltzmann Machine. Industrial Engineering 25 (2022), 152–159. Issue 06.
[14]
Glenn Jocher. 2021. YOLOv5 P6 Models. Website. https://github.com/ultralytics/yolov5/releases/tag/v7.0
[15]
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision – ECCV 2014(Lecture Notes in Computer Science, Vol. 8693), D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars (Eds.). 740–755. https://doi.org/10.1007/978-3-319-10602-1_48
[16]
Ilya Loshchilov and Frank Hutter. 2016. SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv preprint arXiv:1608.03983 (2016).
[17]
Dongliang Luo, Yuxuan Cai, Zihao Yang, Zheyan Zhang, Yu Zhou, and Xiang Bai. 2022. Survey on Industrial Defect Detection with Deep Learning. Scientia Sinica (Informationis) 52, 6 (2022), 1002–1039. https://doi.org/10.1360/SSINF-2021-1164
[18]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Conference(Lecture Notes in Computer Science, Vol. 9351). Munich, Germany, 234–241. https://doi.org/10.1007/978-3-319-24574-4_28 In Proceedings of MICCAI 2015.
[19]
John Smith and Jane Johnson. 2005. Application of CCD industrial cameras in manufacturing. Journal of Electronic Imaging 14, 4 (2005), 1–10. https://doi.org/10.1117/1.2106584
[20]
Liang Wang, Yu Yang, Min Huang, and Qibing Zhu. 2022. Mechanical bruise detection of nectarine based on polarization imaging technology. Laser Technology 46, 6 (2022), 841–849. https://doi.org/10.3969/j.issn.1001-3806.2022.06.012
[21]
Yong Wang, Yuqing Su, Xiangyu Sun, Xiaorui Hao, Yanping Liu, Xiaolong Zhao, Hongsheng Li, Xiushuo Zhang, Jing Xu, Jingjing Tian, Xiaofei Kong, Zhiwei Wang, and Jie Yang. 2022. Principle and Implementation of Stokes Vector Polarization Imaging Technology. Applied Sciences-Basel 12, 13 (JUL 2022). https://doi.org/10.3390/app12136613
[22]
Yuying Yang, Zhanzhong Cui, Ling Wang, and Shuangcheng Wei. 2013. Reflective Laser Polarization Characteristics of Metal Target Surface in the Short-range Detection. Science & Technology Review 31, 11 (2013), 28–32. https://doi.org/10.1016/j.optcom.2013.11.052
[23]
Hongyi Zhang, Moustapha Cissé, Yann N. Dauphin, and David Lopez-Paz. 2017. MixUp: Beyond Empirical Risk Minimization. arXiv preprint arXiv:1710.09412 (2017).
[24]
Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. 2017. Pyramid Scene Parsing Network. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Honolulu, HI, USA, 6230–6239. https://doi.org/10.1109/CVPR.2017.660 In Proceedings of CVPR 2017.
[25]
Yulong Zhao. 2022. Application of laser welding technology in power battery manufacturing. World Manufacturing Engineering & Market 36, 3 (2022), 64:1–64:5. https://doi.org/10.16670/j.cnki.issn.2689-2888.2022.03.018
[26]
Chunyan Zhu, Xu Guo, and Shaohui Zou. 2022. Impact of information and communications technology alignment on supply chain performance in the Industry 4.0 era: mediation effect of supply chain integration. Journal of Industrial and Production Engineering 39, 7 (OCT 3 2022), 505–520. https://doi.org/10.1080/21681015.2022.2099472
Index Terms
- A Few-shot Learning Method for the Defect Inspection of Lithium Battery Sealing Nails
Recommendations
Few-shot semantic segmentation for industrial defect recognition
AbstractIn modern manufacturing, vision-based defect recognition is an important technology to guarantee product quality. Deep learning-based vision recognition methods have made great progress in accuracy and generality than traditional vision methods. ...
Highlights- A few-shot segmentation method based on the comparison of normal and abnormal products is applied to defect detection.
- A new industrial dataset for few-shot defect detection, Industrial-5i, is proposed.
- An L2 distance calculation ...
Application of Deep Learning in Surface Defect Inspection of Ring Magnets
Services Computing – SCC 2019AbstractWe present a method of inspecting surface defects of ring magnets by using deep learning technology, and the inspection system developed utilizing this method has achieved much better accuracy and speed than human inspectors in actual production ...
A new approach for actinic defect inspection of EUVL multilayer mask blanks: Standing wave photoemission electron microscopy
Extreme ultraviolet lithography (EUVL) at 13.5nm is the next generation lithography technique capable of printing sub-50nm structures. With decreasing feature sizes to be printed, the requirements for the lithography mask also become more stringent in ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2023
1025 pages
ISBN:9798400700705
DOI:10.1145/3603781
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 July 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Shenzhen Science and Technology Program
Conference
CNIOT'23
CNIOT'23: 2023 4th International Conference on Computing, Networks and Internet of Things
May 26 - 28, 2023
Xiamen, China
Acceptance Rates
Overall Acceptance Rate 39 of 82 submissions, 48%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 424Total Downloads
- Downloads (Last 12 months)357
- Downloads (Last 6 weeks)29
Reflects downloads up to 12 Dec 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in