Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Artículo Open Access |
| Published: |
Wiley
2025
|
| Subjects: | |
| Online Access: | https://sid.onlinelibrary.wiley.com/doi/10.1002/sdtp.18721 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1867016431364734976 |
|---|---|
| author | Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu |
| author_facet | Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu |
| collection | Wiley Open Access |
| contents | 6‐3: A novel LCD demura algorithm based on deep learning Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu SID Symposium Digest of Technical Papers Since its proposal in 1968, LCD has held an important position in the display field due to its mature technology and low cost advantages[1]. In order to eliminate mura defects in VA‐LCD panels, the traditional Demura method requires taking multiple images of different graylevel, fitting a full graylevels brightness curve, and then calculating compensation values. The long photography time affects the production line capacity. Therefore, the paper proposes a Demura method based on deep learning, which only requires taking a single graylevel image as the input, using the compensation values of traditional schemes as learning labels,and using U‐shaped neural network for model training, to predict the compensation values of different binding point graylevels. While greatly improving efficiency, it can achieve the effect of industry standard schemes. The experimental results show that after adopting this scheme, the number of photos taken can be reduced from 7 to 1, the Demura efficiency can be improved by 51%, the compensation data prediction error is 0.3%, and the panel uniformity is consistent with the traditional schemes; 10.1002/sdtp.18721 http://onlinelibrary.wiley.com/termsAndConditions#vor |
| doi_str_mv | 10.1002/sdtp.18721 |
| format | Artículo Open Access |
| id | wiley_oa_10_1002_sdtp_18721 |
| institution | Wiley Open Access |
| license_str_mv | http://onlinelibrary.wiley.com/termsAndConditions#vor |
| publishDate | 2025 |
| publisher | Wiley |
| record_format | wiley_oa |
| spellingShingle | 6‐3: A novel LCD demura algorithm based on deep learning Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu SID Symposium Digest of Technical Papers 6‐3: A novel LCD demura algorithm based on deep learning Yixin Xiao Tao He Yu Wu Dengxia Zhao Bin Zhao Wei Yang Yangxing Liu SID Symposium Digest of Technical Papers Since its proposal in 1968, LCD has held an important position in the display field due to its mature technology and low cost advantages[1]. In order to eliminate mura defects in VA‐LCD panels, the traditional Demura method requires taking multiple images of different graylevel, fitting a full graylevels brightness curve, and then calculating compensation values. The long photography time affects the production line capacity. Therefore, the paper proposes a Demura method based on deep learning, which only requires taking a single graylevel image as the input, using the compensation values of traditional schemes as learning labels,and using U‐shaped neural network for model training, to predict the compensation values of different binding point graylevels. While greatly improving efficiency, it can achieve the effect of industry standard schemes. The experimental results show that after adopting this scheme, the number of photos taken can be reduced from 7 to 1, the Demura efficiency can be improved by 51%, the compensation data prediction error is 0.3%, and the panel uniformity is consistent with the traditional schemes; 10.1002/sdtp.18721 http://onlinelibrary.wiley.com/termsAndConditions#vor |
| title | 6‐3: A novel LCD demura algorithm based on deep learning |
| topic | SID Symposium Digest of Technical Papers |
| url | https://sid.onlinelibrary.wiley.com/doi/10.1002/sdtp.18721 |