Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Polaroid appearance defect real-time detection method

A technology for real-time detection and appearance defects, applied in neural learning methods, image data processing, biological neural network models, etc., can solve the problems of poor real-time detection and achieve fast detection speed, strong real-time detection, and high detection accuracy.

Pending Publication Date: 2022-01-21
TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of poor real-time performance of the existing polarizer appearance defect detection method, the present invention provides a polarizer appearance defect real-time detection method

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
  • Polaroid appearance defect real-time detection method
  • Polaroid appearance defect real-time detection method
  • Polaroid appearance defect real-time detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] A method for real-time detection of a polarizer appearance defect, the method is realized by the following steps:

[0044]Step 1: First use the camera to take pictures of polarizers, and then perform data expansion on the captured pictures of polarizers to obtain a polarizer data set; the polarizer data set includes a training set, a verification set, a test set, and the original polarizer big picture;

[0045] Step 2: Improve the backbone network and CSP BLOCK module of the YOLOv4-Tiny network model to obtain the YOLOv4-Tiny-C network model;

[0046] Step 3: First use the training set in the polarizer data set to train the YOLOv4-Tiny-C network model, then use the test set in the polarizer data set to test the detection accuracy of the YOLOv4-Tiny-C network model, and output the prediction map;

[0047] Step 4: Use model pruning technology to prune the YOLOv4-Tiny-C network model to obtain the Pruning-YOLOv4-Tiny-C network model;

[0048] Step 5: First write the imag...

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 relates to a polaroid appearance defect detection technology, in particular to a polaroid appearance defect real-time detection method. According to the invention, the problem of poor detection real-time performance of the existing polaroid appearance defect detection method is solved. The invention relates to a real-time polaroid appearance defect detection method, which is realized by adopting the following steps of: step 1, shooting a polaroid picture by using a camera, and carrying out data expansion on the shot polaroid picture to obtain a polaroid data set; step 2, improving a backbone network of the YOLOv4-Tiny network model and a CSP BLOCK module; step 3, firstly training the YOLOv4-Tiny-C network model, and then testing the detection precision of the YOLOv4-Tiny-C network model; step 4, carrying out pruning operation on the YOLOv4-Tiny-C network model; and step 5, segmenting the original large polaroid image in the polaroid data set into small polaroid images, and then inputting the small polaroid images into the Pruning-YOLOv4-Tiny-C network model to carry out defect detection. The polaroid appearance defect detection device is suitable for polaroid appearance defect detection.

Description

technical field [0001] The invention relates to a detection technology for a polarizer appearance defect, in particular to a real-time detection method for a polarizer appearance defect. Background technique [0002] Polarizer is a common polarized optical element, which is widely used in liquid crystal displays and various imaging equipment and instruments. During the production and transportation of polarizers, appearance defects such as dirt, scratches, and bubbles will inevitably form, which will affect the performance and quality of polarizers. Therefore, in order to ensure the performance and quality of the polarizer, it is necessary to detect the appearance defects of the polarizer. [0003] With the development of artificial intelligence technology, the detection method of polarizer appearance defect based on deep learning has become the mainstream method of polarizer appearance defect detection because of its high detection accuracy. However, due to the limitation...

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): G06T7/00G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30108G06N3/045G06F18/241
Inventor 谢新林赵文晶王银李春霖张林谢刚
Owner TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com