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

A Feature Extraction and Classification Method for Strip Surface Defects

A technology of feature extraction and classification method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., and can solve the problems of classification accuracy and efficiency conflicts

Inactive Publication Date: 2017-01-25
NORTHEASTERN UNIV LIAONING
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual classification problem, there is a conflict between the classification accuracy and efficiency of the traditional support vector machine

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 Feature Extraction and Classification Method for Strip Surface Defects
  • A Feature Extraction and Classification Method for Strip Surface Defects
  • A Feature Extraction and Classification Method for Strip Surface Defects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] Embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0088] The embodiment of the present invention adopts a feature extraction and classification method for steel strip surface defects to process the defects of the steel strip, and the process is as follows figure 1 shown, including the following steps:

[0089] Step 1: Extract the reference sampling size table of the strip steel surface defect sample database;

[0090] The reference sampling size table is obtained on the basis of analyzing the training sample library of strip surface defects, which can avoid the influence of scale on the feature extraction of defect samples. The training library in the embodiment of the present invention is a sample extracted from the strip surface defect detection system on site, and contains six types of defect sample sets, which are: cracks, scars, holes, scale, curling and scratches .

[0091] Step 1-1: ...

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

A feature extraction and classification method for strip surface defects belongs to the field of pattern recognition and image processing. Extract the benchmark sampling size table of the strip surface defect sample database; obtain the benchmark sampling image, construct the gradient size-direction co-occurrence matrix; construct the gray-scale size-direction co-occurrence matrix for the defect area of ​​the benchmark sampling image; generate training of feature vector samples Library; use the method of combining K-nearest neighbor and R-nearest neighbor to prune the training sample set and extract the multiple factor; and use the multiple factor of the pruned sample to improve the classifier; obtain a multi-category classifier model; according to the benchmark sampling size table , convert the defect test samples into benchmark sampling images, then extract 25-dimensional feature quantities and input them into the multi-category classifier model to complete automatic identification of defects. The invention can achieve unchanged scale and rotation, suppress the influence of other adverse factors, and improve the efficiency and accuracy of identification.

Description

technical field [0001] The invention belongs to the field of pattern recognition and image processing, and in particular relates to a method for defect feature extraction and defect classification in the direction of defect recognition on the surface of strip steel. Background technique [0002] In recent years, with the ever-increasing demand for high-quality strip steel products and increasingly fierce market competition, the detection of surface defects has become an important technical support for iron and steel enterprises to implement strip quality monitoring and control. Various types of defects will appear during the production and processing of strip steel, such as: cracks, scars, holes, scale, curling, scratches, etc. An important process of surface defect monitoring is to identify and distinguish these defects in order to quickly deal with and control product quality problems. The process of strip surface defect identification mainly includes four links: defect p...

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): G06K9/62G06K9/46
Inventor 王安娜储茂祥巩容芬
Owner NORTHEASTERN UNIV LIAONING
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