A display panel appearance defect detection network and its defect detection method

A defect detection and appearance defect technology, applied in the field of defect detection, can solve the problem of low detection accuracy, achieve the effect of reducing the demand for sample size and improving accuracy

Active Publication Date: 2022-02-01
WUHAN JINGLI ELECTRONICS TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the present invention provides a display panel appearance defect detection network and its defect detection method to solve or at least partially solve the technical problem of low detection accuracy in 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
  • A display panel appearance defect detection network and its defect detection method
  • A display panel appearance defect detection network and its defect detection method
  • A display panel appearance defect detection network and its defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment provides a display panel appearance defect detection network, including: at least two feature extraction modules, at least two detection prediction output modules, an upsampling module and an output layer,

[0043] The feature extraction module is used to perform feature extraction on the image to be processed, and output the feature map corresponding to the position and depth; each feature extraction module is connected in a dense connection mode, and each feature extraction module includes four DBL modules, And the four DBL modules are connected in a dense connection way;

[0044] The up-sampling module upsamples feature maps with different resolutions to feature maps with the same resolution, and outputs them to the detection and prediction output module;

[0045] The detection and prediction output module is used to output the prediction result of the corresponding scale after cascading and convoluting the received feature map;

[0046] The output l...

Embodiment 2

[0077] This embodiment provides a defect detection method, including:

[0078] Input the image of the panel to be processed into the defect detection network described in Embodiment 1 to obtain a defect detection result.

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 panel appearance defect detection network and a defect detection method thereof, comprising at least two feature extraction modules, at least two detection prediction output modules, an up-sampling module and an output layer, and the image to be processed is processed by the feature extraction module Feature extraction, and output the feature map corresponding to the position and depth, through the upsampling module, the feature map with different resolutions is upsampled to the feature map with the same resolution, and the received feature map is processed by the detection and prediction output module After cascading and convolution dimensionality reduction, the prediction result of the corresponding scale is output; the detection result is obtained through the output layer and then output. The invention not only reduces the requirement of the deep learning model on the number of training samples, but also greatly reduces the over-inspection rate and the under-inspection rate of display panel defect detection, and is more robust.

Description

technical field [0001] The invention relates to the technical field of defect detection, in particular to a display panel appearance defect detection network and a defect detection method thereof. Background technique [0002] In the process of display panel production, there are often defects such as scratches, indentations, fragments, dust, and stains on the display panel, which eventually lead to the output of the display panel quality and finished product level. Therefore, in the process of manufacturing the display panel, it is very important to perform defect detection on the various components that make up the display panel and the surface of the display panel that is finally assembled successfully. At present, the detection of each component of the display panel and the display panel mainly relies on human eye observation and traditional image processing algorithms for detection. Defect detection based on human eyes not only has strong subjective factors; moreover, ...

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): G06T7/00G06N3/04
CPCG06T7/0004G06T2207/30121G06N3/045
Inventor 马卫飞张胜森郑增强
Owner WUHAN JINGLI ELECTRONICS TECH
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