Detection method of organic light-emitting diodes based on small sample deep learning.
In order to solve the surface detection problems of low accuracy, low precision and inability to automate in the production process of late-model display panels, a little sample-based deep learning organic light-emitting diodes detection model SmartMuraDetection is proposed. First, aiming at the det...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0297642 |
| _version_ | 1797322344300019712 |
|---|---|
| author | Hua Qiu Jin Huang Yi-Cong Feng Peng Rong |
| author_facet | Hua Qiu Jin Huang Yi-Cong Feng Peng Rong |
| author_sort | Hua Qiu |
| collection | DOAJ |
| description | In order to solve the surface detection problems of low accuracy, low precision and inability to automate in the production process of late-model display panels, a little sample-based deep learning organic light-emitting diodes detection model SmartMuraDetection is proposed. First, aiming at the detection difficulty of low surface defect contrast, a gradient boundary enhancement algorithm module is designed to automatically identify and enhance defects and background gray difference. Then, the problem of insufficient little sample data sets is solved, Poisson fusion image enhancement module is designed for sample enhancement. Then, a TinyDetection model adapted to small-scale target detection is constructed to improve the detection accuracy of defects in small-scale targets. Finally, SEMUMaxMin quantization module is proposed as a post-processing module for the result images derived from network model reasoning, and accurate defect data is obtained by setting a threshold filter. The number of sample images in the experiment is 334. This study utilizes an organic light-emitting diodes detection model. The detection accuracy of surface defects can be improved by 85% compared with the traditional algorithm. The method in this paper is used for mass production evaluation in the actual display panel production site. The detection accuracy of surface defects reaches 96%, which can meet the mass production level of the detection equipment in this process section. |
| first_indexed | 2024-03-08T05:12:59Z |
| format | Article |
| id | doaj.art-354f85b7e5ac49c3b50f0f2d1803b1df |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-03-08T05:12:59Z |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-354f85b7e5ac49c3b50f0f2d1803b1df2024-02-07T05:31:25ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01192e029764210.1371/journal.pone.0297642Detection method of organic light-emitting diodes based on small sample deep learning.Hua QiuJin HuangYi-Cong FengPeng RongIn order to solve the surface detection problems of low accuracy, low precision and inability to automate in the production process of late-model display panels, a little sample-based deep learning organic light-emitting diodes detection model SmartMuraDetection is proposed. First, aiming at the detection difficulty of low surface defect contrast, a gradient boundary enhancement algorithm module is designed to automatically identify and enhance defects and background gray difference. Then, the problem of insufficient little sample data sets is solved, Poisson fusion image enhancement module is designed for sample enhancement. Then, a TinyDetection model adapted to small-scale target detection is constructed to improve the detection accuracy of defects in small-scale targets. Finally, SEMUMaxMin quantization module is proposed as a post-processing module for the result images derived from network model reasoning, and accurate defect data is obtained by setting a threshold filter. The number of sample images in the experiment is 334. This study utilizes an organic light-emitting diodes detection model. The detection accuracy of surface defects can be improved by 85% compared with the traditional algorithm. The method in this paper is used for mass production evaluation in the actual display panel production site. The detection accuracy of surface defects reaches 96%, which can meet the mass production level of the detection equipment in this process section.https://doi.org/10.1371/journal.pone.0297642 |
| spellingShingle | Hua Qiu Jin Huang Yi-Cong Feng Peng Rong Detection method of organic light-emitting diodes based on small sample deep learning. PLoS ONE |
| title | Detection method of organic light-emitting diodes based on small sample deep learning. |
| title_full | Detection method of organic light-emitting diodes based on small sample deep learning. |
| title_fullStr | Detection method of organic light-emitting diodes based on small sample deep learning. |
| title_full_unstemmed | Detection method of organic light-emitting diodes based on small sample deep learning. |
| title_short | Detection method of organic light-emitting diodes based on small sample deep learning. |
| title_sort | detection method of organic light emitting diodes based on small sample deep learning |
| url | https://doi.org/10.1371/journal.pone.0297642 |
| work_keys_str_mv | AT huaqiu detectionmethodoforganiclightemittingdiodesbasedonsmallsampledeeplearning AT jinhuang detectionmethodoforganiclightemittingdiodesbasedonsmallsampledeeplearning AT yicongfeng detectionmethodoforganiclightemittingdiodesbasedonsmallsampledeeplearning AT pengrong detectionmethodoforganiclightemittingdiodesbasedonsmallsampledeeplearning |