A Learning Method for Display Panel Defect Classification
A technology for display panel defects and learning methods, applied in the field of display panel detection, can solve the problems of difficult control of gray uniformity, high false detection rate, low detection efficiency, etc., and achieve the effect of improving detection efficiency and accuracy
Active Publication Date: 2019-08-09
WUHAN JINGCE ELECTRONICS GRP CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The display panel is the main part of the flat-panel display device. Its manufacturing process is complicated, and as the size of the display panel becomes larger, it becomes more and more difficult to control the uniformity of the gray scale. Therefore, it is inevitable that various A variety of display defects, such as bright spots / dark spots / foreign matter bright / BL foreign matter (backlight foreign matter) / white spots / bright dark lines / Mura and other display defects
[0003] At present, the display panel production line generally adopts the method of visually identifying the number and type of display defects to judge the level of the display panel, which has low detection efficiency and high false detection rate.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0033] Embodiment: A display panel defect level judging device capable of learning, classifying and level judging the defect types of the display panel
[0034] Such as figure 1 As shown, a display panel defect level judging device provided in the embodiment of the present invention mainly includes an industrial camera, an image algorithm processing module, a defect classifier learning module, a defect classification module and a defect level judging module. Among them, the industrial camera is mainly used to collect the display screen of the display panel; the image algorithm processing module is mainly used to extract defect feature information from the display screen; the defect classifier learning module is used to provide defect type configuration files and defect feature attribute gradient files; The defect classification module is used to identify the defect type according to the defect type configuration file and the defect characteristic attribute gradient file; the d...
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
Login to View More Abstract
The invention discloses a learning method for classifying defects of a display panel, comprising: introducing defect characteristic attribute description parameters and defect characteristic attribute gradient parameters, wherein the defect characteristic attribute description parameters include characteristic attribute description vectors of various types of defects, The defect characteristic attribute gradient parameter includes the characteristic attribute gradient range α of multiple defect types and the gradient coefficient factor corresponding to the characteristic attribute gradient range α of the multiple defect types; and by adjusting the defect characteristic attribute description parameter or defect characteristic attribute Gradient parameters, so that the imported defect characteristic attribute description parameters and defect characteristic attribute gradient parameters can automatically match the display defect type of the display panel. The present invention continuously improves the introduction of defect characteristic attribute description parameters through the study of known defect types, and continuously converges and optimizes the defect characteristic attribute gradient parameters, which can greatly improve the defect identification and detection efficiency and accuracy of the display panel.
Description
technical field [0001] The invention relates to the technical field of display panel detection, in particular to a learning method for display panel defect classification. Background technique [0002] Flat-panel displays have the advantages of high resolution, high grayscale, and no geometric deformation. At the same time, due to their small size, light weight, and low power consumption, they are widely used in consumer electronics products that people use every day, such as TVs, computers, Mobile phones, tablets, etc. The display panel is the main part of the flat-panel display device. Its manufacturing process is complicated, and as the size of the display panel becomes larger, it becomes more and more difficult to control the uniformity of the gray scale. Therefore, it is inevitable that various A variety of display defects, such as bright spots / dark spots / foreign objects bright / BL foreign objects (backlight foreign objects) / white spots / bright dark lines / Mura and other ...
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
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G06T7/00G06K9/46G06K9/62G06K9/66
CPCG06T7/0004G06V10/464G06V30/194G06F18/2415G06F18/241
Inventor吕东东张胜森邓标华
OwnerWUHAN JINGCE ELECTRONICS GRP CO LTD