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

Method for cloth defect detection by utilizing S transformation signal extraction

A technology for transforming signals and detection methods, applied in image data processing, instruments, calculations, etc., can solve problems such as difficulty in describing textures, inaccurate identification of defect signals, etc., to achieve accurate identification, reduce labor costs, and improve cloth quality control effect of ability

Inactive Publication Date: 2014-04-16
ZHEJIANG NORMAL UNIVERSITY
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The spatial frequency information of the Fourier transform cannot be one-to-one, and the defect signal can only be identified in the frequency domain; although the wavelet transform provides a multi-resolution decomposition information, it is difficult to describe the texture from the wavelet coefficients; the Gabor filter can Capture the frequency components of a specific frequency band from the image and extract features directionally, but the computational complexity of the Gabor filtering method is very high, which limits the application of this method in real-time systems
[0006] Based on the introduction of the above related methods, it can be found that the existing methods for detecting cloth defects focus on the selection of image feature quantities. Such methods will be affected by noise, illumination, and texture features when detecting cloth defects, so that they are not sensitive to the defects. Inaccurate signal discrimination

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 for cloth defect detection by utilizing S transformation signal extraction
  • Method for cloth defect detection by utilizing S transformation signal extraction
  • Method for cloth defect detection by utilizing S transformation signal extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Taking the warp-knitted cloth whose texture feature is A obtained in actual production as an example, the cloth defect detection method utilizing the S-transform signal extraction method of the present invention specifically includes the following steps:

[0050] Step 1), grayscale processing is carried out to the original cloth image, such as figure 2 shown;

[0051] Step 2), accumulating the grayscale values ​​of each column of the grayscaled image, thereby converting the two-dimensional image into a one-dimensional signal f whose abscissa corresponds to the original image abscissa (ie pixel position), and the ordinate is the grayscale accumulation value (p), such as image 3 shown;

[0052]Step 3), do one-dimensional Stockwell transform (one-dimensional S transform) to the obtained one-dimensional signal f (p), obtain the time-frequency diagram S (p, f) of the S transform coefficient modulus value of the one-dimensional signal, the time-frequency The abscissa of ...

Embodiment 2

[0060] Taking the warp-knitted cloth whose texture feature is B obtained in actual production as an example, the cloth defect detection method utilizing the S-transform signal extraction method of the present invention specifically includes the following steps:

[0061] Step 1), grayscale processing is carried out to the original cloth image, such as Figure 9 shown;

[0062] Step 2), accumulating the grayscale values ​​of each column of the grayscaled image, thereby converting the two-dimensional image into a one-dimensional signal f whose abscissa corresponds to the original image abscissa (ie pixel position), and the ordinate is the grayscale accumulation value (p), such as Figure 10 shown;

[0063] Step 3), do one-dimensional Stockwell transform (one-dimensional S transform) to the obtained one-dimensional signal f (p), obtain the time-frequency diagram S (p, f) of the S transform coefficient modulus value of the one-dimensional signal, the time-frequency The abscissa ...

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 method for cloth defect detection by utilizing S transformation signal extraction and belongs to the field of digital image processing. The method comprises the steps of utilizing a projection method to perform gray energy accumulation, and converting warp knitting cloth images into one-dimensional signals; utilizing an S transformation signal extraction method to retain information of defect signals in an S transformation domain to perform S inversion transformation on the information, and extracting the defect signals; performing threshold segmentation on the extracted defect signals in a spatial domain, and obtaining defects and defect position information. The method for cloth defect detection can replace a manual detection link in the cloth production process, improve cloth quality control capability and reduce labor cost simultaneously; the method is not subject to influences of noise, illumination and texture features simultaneously, and the defect signals are judged more accurately in the spatial domain.

Description

technical field [0001] The invention relates to a cloth defect detection method extracted by S transform signal, which belongs to the field of digital image processing. Background technique [0002] Cloth defect detection is an important link in the process of cloth production. At present, the quality of fabrics is mainly inspected manually. However, the reliability of manual inspection is affected by subjective judgments, fatigue and other aspects. The Sari-Sarraf survey found that even the most well-trained manual inspectors can only detect to 70% of fabric defects. Therefore, automatic detection of cloth defects is essential in high-speed production of high-quality fabric products. The development of a fast, efficient, reliable and real-time defect detection system has become inevitable. Cloth defect detection based on image processing technology is a hot and difficult point in the research fields of computer vision, digital image processing and computer graphics. [0...

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): G06T7/00
Inventor 赵翠芳秦悦桐
Owner ZHEJIANG NORMAL UNIVERSITY
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