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

Method and device for quickly detecting defects of double surfaces of large-area transparent substrate based on vision

A visual detection device and transparent substrate technology, applied in measuring devices, material analysis through optical means, instruments, etc., can solve problems such as difficulty in ensuring classification accuracy, complex algorithms, and long time-consuming classification, and achieve intelligent detection and recognition effect

Pending Publication Date: 2017-06-20
GUANGDONG ZHENHUA TECH CO LTD
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If a single classifier is used to identify all kinds of defects on the substrate, it will inevitably lead to complex algorithms and long time-consuming classification, making it difficult to guarantee the accuracy of classification

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
  • Method and device for quickly detecting defects of double surfaces of large-area transparent substrate based on vision
  • Method and device for quickly detecting defects of double surfaces of large-area transparent substrate based on vision
  • Method and device for quickly detecting defects of double surfaces of large-area transparent substrate based on vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with accompanying drawing, the present invention will be further described:

[0030] Such as figure 1 As shown, a fast large-area transparent substrate double-surface defect visual detection method, the specific method is as follows:

[0031] A A large-area transparent substrate is divided into n blocks according to the detection accuracy and lens range;

[0032] B. Configure 2n sets of double-sided visual inspection devices according to the area, and install the visual inspection device according to the position of each positioning point;

[0033] C captures the substrate image, performs machine vision inspection on the substrate image, and then stitches together a large-area transparent substrate overall image;

[0034] D Extract the outer edge of the substrate, and detect the outer dimension and positioning of the substrate;

[0035] E judging whether the standard deviation value among the average values ​​of the number of surface defects in m...

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 method and a device for quickly detecting defects of double surfaces of a large-area transparent substrate based on vision. The method comprises the following steps of dividing the large-area transparent substrate into n areas according to detection precision and a lens range, and arranging 2n sets of double-surface vision detection devices according to areas; according to the position locating of each locating point, installing one vision detection device, and shooting a substrate image; performing robot vision detection on the substrate images, and splicing into an image of the whole large-area transparent substrate. The detection device comprises a PC (personal computer) control system, an upper imaging module, a connector, a lower imaging module, a transparent device and an adjuster. The method has the advantages that detection tasks, such as overall size, are sequentially separated from substrate surface defect detection object and one task is detected each time; the surface defects of the substrate can be quickly, effectively and intelligently detected and identified.

Description

technical field [0001] The invention relates to the technical field of detection and identification of surface defects of transparent substrates, in particular to a visual detection method and device for rapid and large-area double-sided surface defects of transparent substrates. Background technique [0002] Large-area transparent substrates are widely used in optics, optical communications, laser technology, optical imaging and detection, and play an important role in flat display screens, micro cameras, biomedical instruments, and advanced laser systems. For example, the quality control of large-area transparent substrates in the field of flat-panel displays is a key technology for flat-panel displays; each of similar photoelectric products must be equipped with a substrate, and the domestic and international markets have huge demand for substrates. There are 1,000,000,000 pieces. [0003] The detection of substrates includes spectral detection and surface defect detecti...

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): G01N21/958
CPCG01N21/958
Inventor 潘振强
Owner GUANGDONG ZHENHUA TECH CO LTD