TFT-LCD-based defect authenticity detection judgment method and system

A determination method and defect technology, applied in manufacturing computing systems, character and pattern recognition, image data processing, etc., can solve problems such as long matching time, congenital deficiencies, defect image collection, etc., to improve speed and accuracy, and reduce differences. Effect

Active Publication Date: 2022-01-07
ZHAOQING ZHONGDAO OPTOELECTRONICS EQUIP CORP
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The disadvantages of the above-mentioned defect judgment method are: first, it is necessary to collect a large number of defect image databases. When the actual defect image database is insufficient, this judgment method is prone to misjudgment
Second, it is impossible to collect all defect images in the collection of defect image database, and there is a problem of inherent deficiency
Third, when the defect image library becomes larger and larger, the matching time will become longer and longer, lacking sufficient real-time performance

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-based defect authenticity detection judgment method and system
  • TFT-LCD-based defect authenticity detection judgment method and system
  • TFT-LCD-based defect authenticity detection judgment method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, the object of the present invention is to realize the true and false judgment of TFT-LCD defects, and the calculation process is as follows:

[0057] 1. Obtain the location information of the detected defect, such as figure 2 :

[0058] When detecting a defect, record the position information of the defect to obtain the position of the defect.

[0059] Specifically, the defect is detected by a detection algorithm and the location information of the defect is recorded. The detection algorithm can detect defect images and coordinate information thereof according to various defect detection algorithms in the prior art. The present invention does not limit the algorithm for detecting defects, as long as the defects can be detected.

[0060] 2. Obtain defect images, such as image 3 :

[0061] Taking the central position of the defect as the center, the width and height of the minimum repeating unit of the TFT-LCD panel are the basic image s...

Embodiment 2

[0075] This embodiment provides a system for judging the authenticity of defects based on TFT-LCD, such as Figure 16 shown, including:

[0076] Defect location module 100, configured to acquire defect location information;

[0077] A reference image module 200, configured to obtain a defect image and two reference images according to defect location information;

[0078] Aligning the image module 300, for performing local image alignment with the defect image and two reference images, to obtain two alignment images;

[0079] An enhanced filtering module 400, configured to perform image enhancement and Gaussian bilateral filtering on the two alignment images and the defect image;

[0080] The authenticity determination module 500 is used to calculate the absolute value of the difference between the filtered defect image and each filtered alignment image, and compare it with the set threshold to obtain two defect result maps, so as to determine the authenticity of the defect....

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 (Thin Film Transistor-Liquid Crystal Display)-based defect authenticity detection judgment method and system. The method comprises the following steps: acquiring defect position information; acquiring a defect image and two reference images according to the defect position information; performing local image alignment by using the defect image and the two reference images to obtain two aligned images; performing image enhancement and Gaussian bilateral filtering on the two aligned images and the defect image; and calculating the absolute value of the difference between the filtered defect image and each filtered alignment image, and comparing the absolute value with a set threshold value to obtain two defect result images so as to judge the authenticity of the defect. By obtaining the defect image and the reference image of the adjacent position, the difference between the images is reduced, the authenticity of the defect is judged in real time, and the defect judgment speed and accuracy are improved. The visual detection system has the advantages of being high in judgment speed, good in effect and easy to set.

Description

technical field [0001] The invention belongs to the technical field of computer vision detection, and in particular relates to a method and a system for judging the authenticity of defects in TFT-LCD detection. Background technique [0002] With the continuous development and progress of science and technology, computer vision inspection technology has the advantages of fast, efficient and integrated, and is widely used in the field of automation. At present, the optical automatic inspection technology is widely used in the TFT-LCD inspection industry. With the continuous development and improvement of the manufacturing process, the requirements for automatic inspection algorithms are getting higher and higher. Not only does it require a high detection rate of true defects, but also reduce the number of false defects as much as possible. The detection rate is a challenge for automatic detection equipment. Therefore, a more accurate and stable method for judging true and fal...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/70G06T5/00G06K9/62
CPCG06T7/0004G06T7/70G06T5/002G06T2207/10004G06T2207/20028G06T2207/30121G06F18/24Y02P90/30
Inventor 查世华杨义禄李波曾磊关玉萍左右祥
Owner ZHAOQING ZHONGDAO OPTOELECTRONICS EQUIP CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap