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

Fabric defect detection and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines)

A classification method and defect detection technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of unsatisfactory classification accuracy and cumbersome training process of classifiers to achieve good segmentation effect and cumbersome training process , the effect of improving the accuracy rate

Active Publication Date: 2017-11-10
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The classification results of these methods show that the classification accuracy is not ideal, and the classifier training process is cumbersome

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
  • Fabric defect detection and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines)
  • Fabric defect detection and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines)
  • Fabric defect detection and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1: as Figure 1-8 Shown, a fabric defect detection and classification method based on unsupervised segmentation and ELM. First, input the fabric defect image, realize the segmentation of the fabric defect image, and obtain the segmented fabric defect image; secondly, extract the shape and texture features of the segmented fabric defect image and the original defect image, and realize the feature extraction of the fabric defect image; then classify The fabric defect image feature set and label are used as the training set to train the ELM classifier to obtain the parameters of the ELM classifier; finally, the trained classifier is fused according to the Bayesian probability to realize the classification of the fabric defect image and output the classification result of the fabric defect image . The detection and classification method adopted in the present invention has a higher accuracy rate.

[0028] The concrete steps of described method are as follows: ...

Embodiment 2

[0034] Embodiment 2: as figure 1 As shown, the specific steps of the method are as follows: Step1, input fabric defect image G ' , by extracting the image G ' patch {x i} Create data matrix X=[x 1 ,x 2 ,...,x i ,...,x n ],x i ∈ R w , w represents the image G ' patch x i Dimensions, n represents the image G ' patch x i The total number, that is, X contains n column vectors whose dimension is w; based on Euclidean distance E(i)=||x i -x|| 2 , where x is {x i}, eliminate the outliers of the data matrix X to obtain the training data, X c =[x 1 ,x 2 ,...,x i ,...,x c ], 1≤i≤ci ∈ R w , w represents the image G ' patch x i Dimensions, where c represents the training data X c Medium image G ' patch x i Total, i.e. X c Contains c column vectors of dimension w; find a dictionary D that represents the training data X with the least squared error c For each point in , by non-convex function formula (a i is each x of dimension k i coefficient vector), by assum...

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 and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines), and belongs to the fields of computer vision, pattern recognition and image application. Fabric defect images are input, and fabric defect image segmentation is realized to obtain segmented fabric defect images; shape and texture features of the segmented defect images and the original defect images are extracted to realize feature extraction of the fabric defect images; a feature set and labels of the to-be-classified fabric defect images are used as a training set to train an ELM classifier to obtain ELM classifier parameters; and fabric defect image classification is realized through the trained classifier according to Bayesian probability fusion, and a fabric defect image classification result is output. The detection and classification method provided by the invention has a higher accuracy rate.

Description

technical field [0001] The invention relates to a fabric defect detection and classification method based on unsupervised segmentation and ELM (Extreme Learning Machines, ELM for short), belonging to the fields of computer vision, pattern recognition and image application. Background technique [0002] In modern textile production, there are many defects in fabrics, such as holes, oil spots, missing warps, missing wefts, missing stitches, creases, scratches, etc. Fabric defects are caused by failure of weaving machines or unqualified yarn quality, etc. Therefore, detection and classification of fabric defects is a key link in controlling the quality of textiles. The traditional detection and classification of fabric defects is mainly done through manual visual inspection, and the detection and classification results depend on the subjective judgment of the inspector. On the one hand, a lot of work is very boring; on the other hand, long-term observation will cause fatigue t...

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): G06K9/62G06K9/34G06K9/46
CPCG06V10/267G06V10/44G06F18/2415
Inventor 刘骊张建红付晓东黄青松刘利军
Owner KUNMING UNIV OF SCI & TECH
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