Related Experiment Video
Updated: Nov 3, 2025
07:44
Production and Characterization of Vacuum Deposited Organic Light Emitting Diodes
Published on: November 16, 2018
9.1K
Luminance-Degradation Compensation Based on Multistream Self-Attention to Address Thin-Film Transistor-Organic Light
Seong-Chel Park1, Kwan-Ho Park1, Joon-Hyuk Chang1
1Department of Electronics and Computer Engineering, Hanyang University, Seoul 04763, Korea.
Sensors (Basel, Switzerland)
|June 2, 2021
Summary
This study introduces a deep-learning algorithm to fix OLED display burn-in by compensating for luminance degradation. This novel approach reduces costs and complexity compared to traditional methods.
Area of Science:
- Materials Science
- Computer Science
- Electrical Engineering
Background:
- Organic Light-Emitting Diode (OLED) displays suffer from the burn-in phenomenon, causing luminance degradation due to device deterioration.
- Conventional compensation circuits are complex, costly to develop, and expensive to manufacture.
Purpose of the Study:
- To propose a deep-learning algorithm for direct luminance degradation compensation in OLED displays.
- To address the burn-in phenomenon by mitigating pixel-level luminance deviation.
Main Methods:
- A deep-learning algorithm utilizing deep-feature generation and multistream self-attention.
- A deep neural network to identify nonlinear relationships between extracted features and luminance degradation.
- Compensation of luminance degradation estimated from burn-in-related variables.
Main Results:
- Successful compensation of luminance degradation within an error range of 4.56%.
- Demonstrated potential for mitigating the OLED burn-in phenomenon through direct pixel-level compensation.
Conclusions:
- The proposed deep-learning algorithm offers a cost-effective and less complex solution for OLED burn-in.
- This approach allows for circuit reuse by relearning device characteristics, reducing development overhead.
