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

A method for fabric defect detection

A defect detection and fabric technology, applied in the direction of optical testing defects/defects, etc., can solve the problems of affecting the degree of automation of the algorithm, noise interference, insufficient utilization of feature space, etc.

Active Publication Date: 2018-10-23
南通大学技术转移中心有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the present invention is: the existing method of fabric defect detection through machine vision is susceptible to noise interference, often resulting in false detection or missed detection, and inaccurate positioning; the existing defect detection method based on GLCM features does not utilize the feature space. Adequate, parameter setting can not achieve optimal and other shortcomings; further, the existing threshold for segmentation defects is often set artificially, which affects the degree of algorithm automation

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
  • A method for fabric defect detection
  • A method for fabric defect detection
  • A method for fabric defect detection

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0035] The method of the invention mainly includes three steps of obtaining nonlinear mapping functions, learning optimal parameters and detecting defects. The specific implementation is as follows:

[0036] 1. The nonlinear mapping function calculation stage

[0037] For fabric images, the gray levels are often concentrated in a certain interval, rather than uniformly distributed in the entire gray space. If the general GLCM feature extraction method is used, linear quantization will be performed, and a large number of quantization values ​​are not or rarely used, resulting in The generated GLCM matrix is ​​very sparse and cannot fully reflect the texture features of the image. The present invention proposes nonlinear GLCM feature extraction. The basic idea is to quantify according to the occurrence probability of gray levels, refine the high-probability gray-scale intervals, and coarsely quantize the low-probability gray-scale intervals, so that image features can be effect...

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 fabric defect detection method. First, in order to make full use of the feature space and effectively extract image features, a nonlinear gray-scale co-occurrence matrix feature is constructed, and then the nonlinear gray-scale co-occurrence matrix is ​​obtained by learning the non-defective fabric image. The optimal scale and direction parameters for feature extraction and the adaptive defect segmentation threshold are used. Finally, the obtained parameters are used to extract the features of the image to be detected, and the defect area is located by the feature similarity distance measure. The method of the invention can effectively locate the defective area of ​​the fabric, and is less disturbed by noise.

Description

technical field [0001] The invention relates to the technical field of machine vision and video image processing, in particular to a fabric defect detection method. Background technique [0002] The method of detecting fabric defects through artificial vision has many problems such as heavy workload, high missed detection rate, high false detection rate, and being affected by subjective feelings. Automatic detection of fabric defects based on machine vision can effectively solve this problem. question. In order to distinguish the flawed and non-flawed regions, it is a key issue to adopt suitable feature descriptions for fabric images. [0003] The method of extracting fabric image features from the frequency domain, such as wavelet transform, Fourier transform, Gabor filter, etc., first decomposes the image into each defined frequency domain sub-band, and distinguishes the defective area through the difference of sub-band coefficients. Methods for extracting features from ...

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 Patents(China)
IPC IPC(8): G01N21/88
Inventor 董蓉李勃
Owner 南通大学技术转移中心有限公司
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