Multi-stage few-shot micro-defect detection of patterned OLED panel using defect inpainting and multi-scale Siamese neural network

Shujiao Ye, Zheng Wang, Pengbo Xiong, Xinhao Xu, Lintong Du, Jiubin Tan and Weibo Wang ()
Additional contact information
Shujiao Ye: Advanced Nuclear and New Energy Research Institute, Harbin Institute of Technology
Zheng Wang: Harbin Institute of Technology
Pengbo Xiong: Advanced Nuclear and New Energy Research Institute, Harbin Institute of Technology
Xinhao Xu: Advanced Nuclear and New Energy Research Institute, Harbin Institute of Technology
Lintong Du: Harbin Institute of Technology
Jiubin Tan: Harbin Institute of Technology
Weibo Wang: Advanced Nuclear and New Energy Research Institute, Harbin Institute of Technology

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 6, No 12, 2653-2669

Abstract: Abstract Automatic micro-defect detection is crucial for promoting efficiency in the production lines of patterned OLED panels. Recently, deep learning algorithms have emerged as promising solutions for micro-defect detection. However, in real-world industrial scenarios, the scarcity of training data or annotations results in a drop in performance. A multi-stage few-shot micro-defect detection approach is proposed for patterned OLED panels to deal with this problem. Firstly, we introduce a converter from defective to defect-free images based on our redesigned Vector Quantized-Variational AutoEncoder (VQ-VAE), aiming to inpaint defects with normal textures. Next, we exploit a region-growing method with automatic seed points to obtain the defect’s segmentation and geometric parameters in each image block. Reliable seed points are provided by structural similarity index maps between defective sub-blocks and reconstructed reference. Finally, a multi-scale Siamese neural network is proposed to identify the category of extracted defects. With our proposed approach, detection and classification results of defects can be obtained successively. Our experimental results on samples at different array processes demonstrate the superb adaptability of VQ-VAE, with a defect detection rate ranging from 90.0% to 96.0%. Additionally, compared with existing classification models, our multi-scale Siamese neural network exhibits an impressive 98.6% classification accuracy for a long-tailed defect dataset without overfitting. In summary, the proposed approach shows great potential for practical micro-defect detection in industrial scenarios with limited training data.

Keywords: Defect detection; Few-shot learning; Image inpainting; Vector Quantized-Variational AutoEncoder; Siamese neural network (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02168-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:6:d:10.1007_s10845-023-02168-3

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02168-3

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().