journal article·2022-12

In‐line mura detection using machine learning and subspace method in display manufacturing

Satoru Tomita, Prarinya Siritanawan, Kazunori Kotani

Publisher page

Abstract

Abstract This paper discusses the automatic detection of mura, non‐uniformity of brightness or color, which has been a long‐standing challenge in the display industries. Our purpose is to develop a method using machine learning, which automatically detects and classifies mura in the front‐end process. This will enable prompt feedback to the manufacturing process and contribute to improvement of the productivity. We propose “Progressive Hybrid model,” which is based on the human visual perception and consists of a multiclass CNN (Convolutional Neural Network), a 2‐class residual neural network, and a 2‐class CNN. The two 2‐class models based on the subspace method to reproduce the boundary‐samples in the human visible test are for accurate classification between Normal displays and weak mura. To reproduce the appropriate test‐images used in the human visible test, we enhance contrast of 8000 images of the dataset obtained from an OLED (Organic Light Emitting Diode) manufacturing line. The evaluation results show improvement of the accuracy from 0.830 in the general application of CNN to 0.884 in the proposed model. The proposed model is particularly effective to improve classification of Normal displays, which is usually the most numerous in the manufacturing, and thus further beneficial in the practical use.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Industrial Vision Systems and Defect Detection · Color Science and Applications · Visual Attention and Saliency Detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Japan Display Inc Chiba Japan

Japan Advanced Institute of Science and Technology Ishikawa Japan

References (31)

Show source-provided references
1. 10.1109/2944.48839710.1109/2944.488397 ↗
2. TroutmanRR JenkinsLC PolastreRJ WisnieffRL. "Characterization of TFT/LCD Arrays" Conference Record of the 1991 International Display Research Conference p.231–234.10.1109/DISPL.1991.167477 ↗
3. Flat‐panel in‐process test, repair, and inspection: An overview
4. 10.1016/0167-9317(94)90052-310.1016/0167-9317(94)90052-3 ↗
5. 10.1889/1.183228710.1889/1.1832287 ↗
6. 10.2493/jjspe.63.52010.2493/jjspe.63.520 ↗
7. 10.1002/sdtp.1410010.1002/sdtp.14100 ↗
8. 10.1002/sdtp.1464610.1002/sdtp.14646 ↗
9. 10.1002/sdtp.1409710.1002/sdtp.14097 ↗
10. TFT‐LCD mura defect detection based on ICA and multi‐channels fusion
11. 10.1109/TII.2016.252219110.1109/TII.2016.2522191 ↗
12. 10.1002/sdtp.1409910.1002/sdtp.14099 ↗
13. 10.1002/sdtp.1409610.1002/sdtp.14096 ↗
14. 10.1002/sdtp.1464510.1002/sdtp.14645 ↗
15. 10.1002/sdtp.1565710.1002/sdtp.15657 ↗
16. 10.1002/sdtp.1565810.1002/sdtp.15658 ↗
17. 10.1002/sdtp.1565910.1002/sdtp.15659 ↗
18. AI analysis of HOP circuit failure and improvement
19. 10.1002/sdtp.1579310.1002/sdtp.15793 ↗
20. 10.1002/sdtp.1409810.1002/sdtp.14098 ↗
21. 10.1002/sdtp.1562810.1002/sdtp.15628 ↗
22. 10.1002/sdtp.1562910.1002/sdtp.15629 ↗
23. 10.1002/sdtp.1563110.1002/sdtp.15631 ↗
24. 10.1002/sdtp.1563210.1002/sdtp.15632 ↗
25. 10.1002/047122132510.1002/0471221325 ↗
26. Variation control by boundary‐samples in visual inspection (in Japanese)
27. 10.1109/5.72679110.1109/5.726791 ↗
28. KrizhevskyA SutskeverI HintonGE. “ImageNet classification with deep convolutional neural networks” In NIPS.2012;1106–1114.
29. Chollet F · 2017
30. HeK ZhangX RenS SunJ. “Deep Residual Learning for Image Recognition” arXiv:1512.03385v1 [cs.CV].2015.
31. Available online:https://keras.io/api/applications/resnet/(accessed on 13 March 2022).