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

Textile quality detection algorithm and apparatus based on visual identification technology

A visual recognition and detection algorithm technology, applied in the field of visual recognition, can solve problems such as poor product quality and corporate reputation, high missed detection rate, and impact, and achieve the effect of ensuring high-speed production process, ingenious cooperation, and high efficiency

Inactive Publication Date: 2021-07-20
JINHUA VOCATIONAL TECH COLLEGE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of industrialization in our country, the production speed of various industrial products has been greatly improved. Due to the various types of defects in industrial products, the defect identification of products in traditional industries has always been done manually, but manual identification Defects will be affected by many factors, and the missed detection rate is very high, which has a negative impact on product quality and corporate reputation. Therefore, the present invention provides a textile quality detection algorithm and equipment based on visual recognition technology, which can automatically learn and identify multiple defects. defects, high accuracy, saving a lot of manpower and material resources

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
  • Textile quality detection algorithm and apparatus based on visual identification technology
  • Textile quality detection algorithm and apparatus based on visual identification technology
  • Textile quality detection algorithm and apparatus based on visual identification technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] A textile quality detection algorithm based on visual recognition technology. The textile quality detection algorithm based on visual recognition technology uses a regional convolutional neural network, including an input layer, a convolutional layer, a downsampling layer, a fully connected layer, and an output layer. The textile quality inspection algorithm based on visual recognition technology includes the following steps:

[0039] Step 1: Acquisition of the image of the textile to be detected;

[0040] Step 2: Generate target candidate regions;

[0041] Step 3: defect feature extraction;

[0042] Step 4: Identify and locate defect features;

[0043] Step Five: Find the best location information.

[0044] The way to obtain the textile image is to input the image into the regional convolutional neural network. The features extracted by the regional convolutional neural network include defect category, defect position, defect position coordinates and the size of the...

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 textile quality detection algorithm and apparatus based on a visual identification technology, the textile quality detection algorithm based on the visual identification technology adopts a regional convolutional neural network, and the regional convolutional neural network comprises an input layer, a convolutional layer, a down-sampling layer, a full-connection layer and an output layer. During working, an image to be detected needs to be transmitted into the convolutional neural network. The image processing process comprises target candidate region generation, defect feature extraction, defect specific identification and positioning and optimal defect position determination, the defect detection based on the regional convolutional neural network is an end-to-end detection model, image preprocessing is not needed, the defect position can be accurately given while the defect is identified, and the invention has the characteristics of high efficiency and accuracy.

Description

technical field [0001] The invention relates to the technical field of visual recognition, in particular to a textile quality detection algorithm and equipment based on visual recognition technology. Background technique [0002] With the rapid development of industrialization in our country, the production speed of various industrial products has been greatly improved. Due to the various types of defects in industrial products, the defect identification of products in traditional industries has always been done manually, but manual identification Defects will be affected by many factors, and the missed detection rate is very high, which has a negative impact on product quality and corporate reputation. Therefore, the present invention provides a textile quality detection algorithm and equipment based on visual recognition technology, which can automatically learn and identify multiple defects. Such defects, high accuracy, save a lot of manpower and material resources. Con...

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): G06T7/00G06T7/73G06K9/46G06K9/62G01N21/88G01N21/898
CPCG06T7/0004G06T7/73G01N21/8851G01N21/898G01N2021/8887G01N2021/8854G06T2207/10004G06T2207/20084G06T2207/20081G06T2207/30124G06V10/40G06F18/24
Inventor 刘日仙
Owner JINHUA VOCATIONAL TECH COLLEGE
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