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

Textile defect type identification method based on artificial intelligence

A defect type, artificial intelligence technology, applied in the field of textiles, can solve the problems of low recognition efficiency, dependence on recognition effect, high false detection rate and missed detection rate, and achieve the effect of high recognition accuracy, fast detection speed and low cost

Active Publication Date: 2022-07-15
绍兴柯桥奇诺家纺用品有限公司
View PDF12 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the effect of manual textile defect recognition depends heavily on the subjective experience, attention and judgment of the tester, the false detection rate and missed detection rate are too high, and the recognition efficiency is low

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 defect type identification method based on artificial intelligence
  • Textile defect type identification method based on artificial intelligence
  • Textile defect type identification method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The embodiment of the present invention provides an artificial intelligence-based textile defect type identification method, such as figure 1 shown, including:

[0058] S101. Obtain a grayscale image of the surface of the textile to be detected.

[0059] Among them, grayscale image, also known as grayscale image. The relationship between white and black is divided into several levels according to the logarithmic relationship, which is called grayscale. Grayscale is divided into 256 levels.

[0060] S102. Perform clustering processing on the grayscale image to obtain all the first clusters.

[0061] Among them, the process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects is called clustering.

[0062] S103: Perform Gaussian fitting according to the gray value of each pixel in each first cluster, calculate the KL divergence between the Gaussian models corresponding to each first cluster, and obtain all the fi...

Embodiment 2

[0077] The invention mainly detects and classifies the defects on the surface of the textiles by means of artificial intelligence, and further identifies the types of defects of the textiles by performing feature extraction on the image data to identify the defects of the detection surface and other conditions. The method of the invention can realize the detection of defects on the surface of textiles and classify and identify the defect types, so as to provide specific defect categories for textile workers, so that the workers can take corresponding repair measures for different defect types.

[0078] The embodiment of the present invention provides an artificial intelligence-based textile defect type identification method, such as figure 2 shown, including:

[0079] S201. Collect an image of the textile to be detected.

[0080] First, a device is deployed just above the textile to collect images, and the camera's shooting range and angle are adjusted by the implementer acc...

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 the field of textiles, in particular to a textile defect type identification method based on artificial intelligence, and the method comprises the steps: obtaining a textile surface gray-scale map; clustering the grey-scale map to obtain a first cluster; gaussian fitting is carried out according to the gray values of the pixel points in the first clustering clusters, KL divergence between every two Gaussian models is calculated, and similarity between every two first clustering clusters is obtained; combining the first clusters according to the similarity to obtain second clusters; obtaining a suspected defect area according to the difference value between each second cluster and the gray average value of the normal textile; obtaining the defect area according to the area of each suspected defect area and the aspect ratio of the minimum enclosing rectangle; cutting the RGB image containing the defect areas to obtain the RGB image of each defect area; and identifying defect types in the textile by utilizing the RGB images of the defect areas. The method is used for identifying the defect type of the textile, and the defect identification accuracy can be improved through the method.

Description

technical field [0001] The invention relates to the field of textiles, in particular to a method for identifying defect types of textiles based on artificial intelligence. Background technique [0002] Defects on the surface of textiles will affect the beauty of subsequent fabrics and even cause quality problems. Defect detection and identification of defect types are key links in textile industrial production. In the textile industry, there are more than 50 kinds of textile defects, most of which are caused by machine failures and yarn problems. Such defects can be divided into six types: dirty yarn, cobweb, warp break, weft combined, thinning and loose yarn. defect. Textiles undergo various inspections and tests during the production process and before entering the market, which is an essential step in the identification of defects on the surface of textiles. [0003] At present, the method for identifying defects on the surface of textiles is mainly manual, which relie...

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): G06T7/00G06T7/11G06T7/90G06K9/62G06V10/762G06V10/74G06V10/82G06N3/04G06N3/08
CPCG06T7/0004G06T7/90G06T7/11G06N3/08G06T2207/20081G06T2207/20084G06T2207/30124G06N3/045G06F18/23G06F18/22Y02P90/30G06T2207/10024
Inventor 杨美琴范春燕
Owner 绍兴柯桥奇诺家纺用品有限公司
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