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

Screen edge outer arc defect detection method based on mold stress receptor

A defect detection and sensor technology, which is applied in the direction of instruments, character and pattern recognition, biological neural network models, etc., can solve the problems of accuracy drop and achieve the effect of avoiding accuracy drop and improving detection efficiency and accuracy

Pending Publication Date: 2021-03-16
苏州协同创新智能制造装备有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the deficiencies of existing products, and provide a screen edge sensor based on mold stress receptors that can effectively improve the detection efficiency and avoid the use of optical methods to detect and reduce the accuracy caused by the optical effect produced by the curved surface of the screen. Method of Arc Defect Detection

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
  • Screen edge outer arc defect detection method based on mold stress receptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] The method for detecting the outer arc defect of the screen edge based on the mold stress receptor of the present invention comprises the following steps:

[0017] Step 1: Use a qualified screen to make a stress receptor mold;

[0018] Step 2: match the edge of the screen of the inspected product 1 with the stress sensing surface 3 of the stress receptor 2 to generate a stress distribution diagram;

[0019] Step 3: Use a convolutional neural network to extract features from the stress distribution map;

[0020] Step 4: Use the convolutional neural network-based target detection technology to classify and regress the extracted defect features, and finally generate a label frame and a confidence probability value at the defect location.

[0021] The stress distribution map corresponds to a real number matrix, which can be equated to a single-channel grayscale im...

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 screen edge outer arc defect detection method based on a mold stress receptor. The method comprises the following steps that 1, manufacturing a stress receptor mold by usinga qualified screen; 2, matching the screen edge of the detected product with the stress sensing surface of the stress sensor to generate a stress distribution diagram; 3, performing feature extractionon the stress distribution diagram by using a convolutional neural network; and step 4, classifying and regressing the extracted defect features by using a target detection technology based on a convolutional neural network, and finally generating a labeling box and a confidence coefficient probability value at the defect position. According to the invention, precision reduction caused by an optical effect generated by an optical method for detecting the cambered surface part of the curved screen can be avoided, and the detection efficiency and precision are effectively improved.

Description

technical field [0001] The invention relates to a defect detection of the outer arc of the edge of a curved OLED screen, more specifically, a method for detecting the defect of the outer arc of the screen edge based on a mold stress receptor. Background technique [0002] The edge material of the curved screen product is an optical glass panel, and the cross-sectional shape is a curved surface. The traditional defect detection method is based on the principle of reflected light or transmitted light intensity detection, which is easily affected by the optical properties of the screen edge material. Using the traditional planar optical sensor to shoot the edge of the curved screen requires correcting the distortion before testing the image. The distortion correction process requires Use interpolation to fill the vacant pixels. The interpolation calculation is generated by adjacent pixel values, which is easy to weaken the defect characteristics and generate errors. [0003] T...

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
IPC IPC(8): G06K9/46G06K9/62G06N3/04
CPCG06V10/44G06V2201/07G06N3/045G06F18/24G06F18/2415
Inventor 殷凯黄羿衡
Owner 苏州协同创新智能制造装备有限公司