Display Bright Spot Correction Using ML-Based Luminance Compensation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Display devices with large substrates face issues of display unevenness due to differences in light exposure between divided regions, leading to noticeable bright spots and reduced image quality, which are difficult to address during manufacturing or post-use deterioration.

Innovation Solution

An image processing system utilizing a machine learning model generated by a learning device that compares and processes image data to minimize display unevenness, including a display device, image capturing device, and a generator, which adjusts pixel luminance to match target values, thereby reducing bright spots and enhancing image quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If divided light exposure is performed to accommodate large substrates, then the substrate size can be increased, but display unevenness occurs due to different light exposure amounts at boundaries between regions

Engineering Contradiction:
Improvesubstrate sizeVSAvoiddisplay uniformity
Core Design Contradiction:
Area of stationary objectVSManufacturing precision

Solution Approach 1:

The patent applies preliminary action by measuring and storing luminance characteristics of each light exposure region before the actual display operation. The control unit stores the luminance characteristic values in advance, allowing for subsequent compensation without requiring physical modification of the display device or re-measurement during operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes parameters by adjusting the drive signals sent to pixels based on their position in different light exposure regions. The control unit modifies the luminance output parameters of pixels at boundaries by referencing the stored luminance characteristic values, thereby compensating for manufacturing variations and achieving uniform display across the entire large substrate.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If image processing is performed to correct display unevenness, then image quality can be improved, but processing time increases

Engineering Contradiction:
Improvedisplay uniformityVSAvoidprocessing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs luminance characteristic measurement and storage in advance during manufacturing. By pre-storing the luminance characteristic values for each region, the system eliminates the need for time-consuming real-time measurement and processing during actual display operation, thus improving display uniformity without increasing processing time.

Inventive Principle:
Principle #10Preliminary action

3Area of stationary object

If mask size is increased to match substrate size, then light exposure coverage is improved, but manufacturing complexity increases when mask cannot be scaled

Engineering Contradiction:
Improvelight exposure coverageVSAvoidmask manufacturing complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent segments the large substrate into multiple smaller light exposure regions that can be processed using standard-sized masks. The control unit divides the display area into multiple regions, each corresponding to a separate light exposure process, allowing the use of available mask sizes while still achieving complete coverage of the large substrate through coordinated processing of multiple regions.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12488440B2Image system display bright spot correction system
Publication Date: 2025.12.02 SEMICON ENERGY LAB CO LTD
  • US12488440B2 patent drawing
  • US12488440B2 patent drawing
  • US12488440B2 patent drawing

AI summary

An image processing system that can reduce display unevenness in an image displayed on a display device is provided. The image processing system includes a display device, an image capturing device, and a learning device. The learning device stores a table representing information on the correspondence between first image data and second image data that is generated by display of an image corresponding to the first image data on the display device and image capturing of the image by the image capturing device. The learning device generates teacher data in accordance with the table and generates a machine learning model with the use of the teacher data generated. Image processing using the machine learning model is performed on image data input to the display device, so that display unevenness in the image displayed on the display device can be reduced.