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

Precise detection method for strip surface defects based on histogram decomposition

A detection method and histogram technology, which is applied in image analysis, image enhancement, image data processing, etc., to achieve the effects of fast detection speed, high detection rate and wide application range

Active Publication Date: 2019-10-15
HEBEI UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The calculation accuracy of some methods needs to be improved, such as: Yuan et al. (Xiao-cui Yuan, Lu-shen Wu, Qingjin Peng, "An improved Otsumethod using the weighted object variance for defect detection," Appl.Surf.Sci., Vol .349, pp.472-484, Sep.2015.) The improved Otsu threshold algorithm proposed can only get good detection results for images with bimodal or close to bimodal histograms

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
  • Precise detection method for strip surface defects based on histogram decomposition
  • Precise detection method for strip surface defects based on histogram decomposition
  • Precise detection method for strip surface defects based on histogram decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] The steps of the accurate detection method for strip surface defects based on histogram decomposition in this embodiment are:

[0081] Step 1, read the image:

[0082] use as figure 2 The detection device shown online acquires the grayscale image I to be detected,

[0083] 1-1: Before defect detection, use a strip stroboscopic light source to provide a light source for the strip surface, and obtain the grayscale image I to be detected through a line array camera and store it in the memory of the computer;

[0084] 1-2: Read the grayscale image I to be detected from the memory of the computer, generate a histogram of the grayscale image to be detected, and obtain each grayscale g i The corresponding frequency f(g i ), where i∈[1,L] and i∈Z,L is the total number of gray levels contained in the gray image to be detected.

[0085] Step 2, collect and determine the sampling points belonging to the background from the histogram of the grayscale image to be detected:

[...

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 the precise detection of surface defects of a strip steel based on histogram decomposition, and the method comprises the following steps: reading an image; collecting a sampling point, which is determined to belong to the background, from a to-be-detected gray scale image histogram; carrying out the fitting of a histogram decomposition curve; defining a membership function (mu)A according to a decomposition curve fc and the frequencies f(gi) corresponding to all gray scales in the to-be-detected gray scale image histogram, wherein the membership function (mu)A is used for representing each gray scale and the degree that a pixel point corresponding to each gray scale belongs to a defect; setting a confidence degree alpha, and generating a membership matrix according to a fuzzy theory and the membership function (mu)A; searching all connected regions in the membership matrix and solving the sum of the membership degrees of all connected regions; setting a connected region threshold value TH, marking all pixel points corresponding to the connected regions as 1 if the sum of the membership degrees of all connected regions is greater than the connected region threshold value TH, judging that the pixel points are defect points, or else marking all the pixel points as zero and determining that the pixel points are non-defect points, thereby achieving the accurate positioning of the defects.

Description

technical field [0001] The invention belongs to the technical field of strip steel surface defect detection, in particular to a method for accurately detecting strip steel surface defects based on histogram decomposition. Background technique [0002] Strip steel is an important raw material for current industrial production and plays a vital role in the current industry. However, due to the influence of the production environment, the wear of the conveying roller and the strip steel, various complex defects are easily produced on the surface of the strip steel. These defects not only affect the appearance of the steel, but also seriously affect the corrosion resistance, fatigue resistance and wear resistance of the product. Its quality has a serious impact, which often causes unpredictable economic losses to enterprises, so related enterprises put forward higher requirements for the surface quality of steel products. In recent years, with the increasing demand for steel, 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T5/40
Inventor 刘坤王合英张珈玮罗娜娜陈海永
Owner HEBEI UNIV OF 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