Unlock instant, AI-driven research and patent intelligence for your innovation.

Display screen defect detection method, training method, device, equipment and medium

A defect detection and display technology, which is applied in the field of artificial intelligence, can solve the problems of low accuracy of display defect detection results, and achieve the effects of rich data, saving computing costs, and reducing the amount of parameters

Inactive Publication Date: 2022-06-28
CHENGDU UNION BIG DATA TECH CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of this application is to provide a display screen defect detection method, training method, device, equipment and medium, aiming to solve the problem of low accuracy of display screen defect detection results obtained through the prior art

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
  • Display screen defect detection method, training method, device, equipment and medium
  • Display screen defect detection method, training method, device, equipment and medium
  • Display screen defect detection method, training method, device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0108] It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0109] The main solution of the embodiments of the present application is to propose a display screen defect detection method, by acquiring the image of the display screen to be detected, and inputting the image of the display screen to be detected into a pre-trained classification detection model to obtain the detection result. Wherein, the detection results include normal display and uneven display, and the classification detection model is obtained by training based on the initial classification detection model; the initial classification detection model includes: a sampling unit, a self-attention unit, and a space pyramid unit; the The sampling unit is used to sample and reorganize the image of the display screen to be detected; the self-attention unit is used to compress the image of the display screen t...

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 display screen defect detection method and device, a training method and device, equipment and a medium. The method comprises the following steps: acquiring an image of a to-be-detected display screen; inputting the image of the display screen to be detected into a pre-trained classification detection model to obtain a detection result; wherein the detection result comprises normal display and non-uniform display, and the classification detection model is obtained based on training of an initial classification detection model; the initial classification detection model comprises a sampling unit, a self-attention unit and a space pyramid unit. A classification detection model composed of the sampling unit, the self-attention unit and the space pyramid unit is adopted to detect the defects of the display screen, the expression ability of image features and the feasibility of the model can be enhanced, the loss of defect feature expression is reduced, compared with traditional manual detection, the detection result is faster and more accurate, and the detection efficiency is improved. The automation degree of the product manufacturing process is improved, and the defect detection accuracy is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a display screen defect detection method, training method, device, equipment and medium. Background technique [0002] The backlight module of the display adopts an edge-lit backlight design. The backlight module includes a backlight and a light guide plate. The backlight is arranged on one side of the light guide plate, and the light emitted by the backlight is transmitted to the display in the display through the light guide plate. panel. However, the design of the edge-lit backlight will cause the brightness of the image displayed on the display to be higher in the area close to the backlight and lower in the area far from the backlight, resulting in uneven brightness and darkness of the display image. [0003] With the development of large-scale, high-resolution, thin and low-power panels, glass substrates are getting thinner and smaller, and th...

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): G06T7/00G06V10/764G06V10/77G06V10/774G06V10/82G06N3/04G06N3/08G06K9/62
CPCG06T7/0004G06N3/08G06T2207/20081G06T2207/20084G06T2207/30121G06N3/048G06N3/045G06F18/213G06F18/24G06F18/214
Inventor 不公告发明人
Owner CHENGDU UNION BIG DATA TECH CO LTD