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

Two-channel fabric defect detection method based on two-dimensional empirical mode decomposition

An empirical mode decomposition and detection method technology, which is applied in image analysis, image data processing, instruments, etc., can solve problems such as inability to adaptive image decomposition, general comparison results, and limited significance of results

Active Publication Date: 2018-07-17
JIANGNAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current image decomposition methods commonly used in the field of defect detection, such as wavelet decomposition, are not based on the characteristics of the image itself, but based on the fixed scale, direction and response function, and cannot adaptively decompose the image into detail scale texture information and roughness. Scale grayscale information
[0003] Two-dimensional empirical mode decomposition is a tool for decomposing images based on the internal eigenmodes of image data, but there are still some problems in the theoretical research of two-dimensional empirical mode decomposition, such as finding extreme points, boundary processing, interpolation and stopping criteria In terms of methods, researchers have proposed different schemes, but there is a lack of systematic comparison, especially for the optimization of a specific application. Only Bhuiyan et al. (2009) compared the performance of different interpolation methods, but in their study they used 8 Neighborhood extreme point method, without boundary processing, and the comparison result is too general, so the significance of its results is limited

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
  • Two-channel fabric defect detection method based on two-dimensional empirical mode decomposition
  • Two-channel fabric defect detection method based on two-dimensional empirical mode decomposition
  • Two-channel fabric defect detection method based on two-dimensional empirical mode decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] (1) For a fabric image with holes and defects (Fig. 2(a)), use geodesic dilation operator to find extreme points, mirror image continuation boundary processing, global thin plate spline interpolation after segmental interpolation and SD≤0.2 stop The optimized 2D empirical mode decomposition of the criterion yields IMF1 (Fig. 2(b)), IMF2 (Fig. 2(c)), IMF3 (Fig. 2(d)) and residuals (Fig. 2(e));

[0076] (2) After merging IMF2 and IMF3 to obtain IMF2+3 (Figure 3(a)), use the μ±3σ threshold method to binarize it to obtain the result of the grayscale detection channel (Figure 3(b));

[0077](3) Measure the Laws texture of IMF1 using the L5L5 template and the W5W5 template to obtain the texture energy (Fig. The energy result is binarized using the μ±3σ threshold method to obtain two binarized results, and the two binarized results are combined to obtain the texture detection channel result (Figure 4(b));

[0078] (4) Merge the result of the gray level detection channel and t...

Embodiment 2

[0080] (1) For a double-weft defect fabric image (Fig. 6(a)), use geodesic expansion operator to find extreme points, mirror image extension boundary processing, global thin plate spline interpolation after segmental interpolation and SD≤0.2 stop The optimized two-dimensional empirical mode decomposition of the criterion, IMF1, IMF2, IMF3 and residuals are obtained;

[0081] (2) After merging IMF2 and IMF3 to obtain IMF2+3, use the μ±3σ threshold method to binarize it to obtain the grayscale detection channel result (Figure 6(b));

[0082] (3) Use the L5L5 template and W5W5 template to measure the Laws texture of IMF1 to obtain the texture energy, and use the μ±3σ threshold method to perform binarization on the texture energy results of the L5L5 template and the texture energy results of the W5W5 template respectively, and obtain two binary values The results of binarization are combined to obtain the result of the texture detection channel (Fig. 6(c));

[0083] (4) Merge the...

Embodiment 3

[0085] (1) For a fabric image with dense road defects (Fig. 7(a)), use geodesic dilatation operator to find extreme points, image continuation boundary processing, global thin-plate spline interpolation after segmental interpolation and SD≤0.2 The optimized two-dimensional empirical mode decomposition of the stopping criterion yields IMF1, IMF2, IMF3 and residuals;

[0086] (2) After merging IMF2 and IMF3 to obtain IMF2+3, use the μ±3σ threshold method to binarize it to obtain the grayscale detection channel result (Figure 7(b));

[0087] (3) Use the L5L5 template and W5W5 template to measure the Laws texture of IMF1 to obtain the texture energy, and use the μ±3σ threshold method to perform binarization on the texture energy results of the L5L5 template and the texture energy results of the W5W5 template respectively, and obtain two binary values The results of binarization are combined to obtain the result of the texture detection channel (Fig. 7(c));

[0088] (4) Merge 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 present invention relates to a dual-channel fabric fault detection method based on two-dimensional empirical mode decomposition. Aiming at each step method and parameters in the fabric image feature two-dimensional empirical mode decomposition, an optimal decomposition method is employed to obtain IMFI consisting of fabric texture information and IMF2+3 consisting of rough scale gray information; the texture energy is extracted by using optimal Laws texture measurement, the binaryzation operation is performed, and a texture detection channel result is obtained; the binaryzation operation of the IMF2+3 is carried out, and a gray detection channel result is obtained; and the texture detection channel result and the gray detection channel result are fused, and the fabric fault detection result is obtained, wherein the pixel with the value of 255 in the result represents a faultless region, and the pixel with the value of 0 in the result represents a fault region. The dual-channel fabric fault detection method based on the two-dimensional empirical mode decomposition solve the problem that the two-dimensional empirical mode decomposition is short of the scheme of fabric image decomposition, and on the basis, provides a dual-channel fabric fault detection method according with a human eye work mode.

Description

technical field [0001] The invention belongs to the technical field of image analysis and processing, and relates to a two-channel fabric defect detection method based on two-dimensional empirical mode decomposition, which is applied to the field of automatic detection and control of textile surface quality. Background technique [0002] In the fabric defect detection method based on machine vision and image processing technology, the most difficult problem is that it is difficult to achieve universality for a wide variety of fabric structures and defect forms. Existing methods usually regard the fabric image as a single object for detection, and when the human eye recognizes defects of different manifestations, mainly defects with obvious grayscale changes and defects with only texture changes, the visual and logical working modes have unique features. Therefore, decomposing the fabric image into texture information and grayscale information on a rough scale is a method wit...

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): G06T7/00G06T7/10
CPCG06T7/0004G06T2207/30124
Inventor 高卫东厉征鑫周建潘如如
Owner JIANGNAN UNIV
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