Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion

A defect detection, multi-channel technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as uneven brightness, color spot mura information loss, mura defects cannot be accurately segmented, etc., to achieve the effect of reducing noise interference

Active Publication Date: 2018-07-17
南京汇川图像视觉技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problems in the prior art, the present invention proposes a TFT-LCDmura defect detection method based on ICA learning and multi-channel fusion; the present invention selects a large number of defect-free samples to construct a training sample set, and uses the FastICA algorithm to separate independent samples from the sample set. The image base, project the test image onto the image base, reconstruct the background image, and then use the thresholding model to accurately segment the mura area in the difference image, and fuse the detection results of the two channels of the gray domain and the S domain as the final The detection results solve the problem that the mura defect cannot be accurately segmented and the color spot mura information is lost due to the uneven brightness of the image background

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion
  • TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion
  • TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] combine figure 1 , a TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion in this embodiment, select a large number of defect-free samples to construct a training sample set, use the FastICA algorithm to separate independent image bases from the sample set, and test the image Project to the image base, reconstruct the background image, and then use the thresholding model to accurately segment the mura area in the difference image, and fuse the detection results of the two channels of the gray domain and the S domain as the final detection result. By introducing a learning mechanism in background reconstruction, the reconstructed image can retain as much background information as possible without being affected by the target; and fully consider the color information of mura defects, and introduce a multi-channel fusion detection scheme. It has good detection results for different types of mura defects, especially for mura defects caused by ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion, and belongs to the field of TFT-LCD display defect detection. This invention uses the FastICA algorithm to separate independent image bases from a large number of sample images, and uses the image base to reconstruct the background image, retaining as much background information as possible without being affected by the target, and then comparing the test image and the background The differential image is thresholded to reduce the interference of potential target areas and noise on target segmentation by setting multiple thresholds. At the same time, taking into account the color information of mura defects, a multi-color channel fusion detection scheme is introduced to take into account different types of mura defect detection. . The invention can adapt to different types of mura defect detection, and has less over-detection and missed detection.

Description

technical field [0001] The invention belongs to the technical field of TFT-LCD display defect detection, and in particular relates to a TFT-LCD mura defect detection method based on ICA learning and multi-channel fusion. Background technique [0002] TFT-LCD is currently the most popular display device, and its application fields involve industrial control, portable mobile products, desktop displays, televisions, aviation, medical and public display fields, etc. With the increasing complexity of TFT-LCD manufacturing technology, the probability of mura defects appearing in TFT-LCD screens increases accordingly. The mura defect is used to describe the brightness imbalance that people perceive when viewing a display. It is a low-contrast object with no fixed shape and blurred edges. The main reasons are defects in circuits or structures and uneven material properties. At present, most enterprises use the traditional manual method for mura defect detection, which has a series ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T5/00
CPCG06T7/0004G06T2207/20228G06T2207/10024G06T5/70
Inventor 李勃王秀董蓉朱赛男何玉婷史德飞
Owner 南京汇川图像视觉技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com