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

Metal surface fine defect detection method based on vision

A metal surface and defect detection technology, applied in the field of computer vision, can solve the problems of missed detection and false detection, high missed detection rate, low positive detection rate, etc., and achieve the effect of solving high missed detection rate and rapid identification

Pending Publication Date: 2019-03-26
WUYI UNIV
View PDF5 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has a low positive detection rate and a high missed detection rate for subtle defects on the metal surface, and the detection method is inefficient. check

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
  • Metal surface fine defect detection method based on vision
  • Metal surface fine defect detection method based on vision
  • Metal surface fine defect detection method based on vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] An embodiment of the present invention provides a vision-based detection method for fine defects on a metal surface.

[0022] like Figure 1-7 As shown, a vision-based metal surface fine defect detection method provided by the embodiment of the present invention, its specific steps are:

[0023] S1. Collect 4 images of the metal surface to be tested at different illumination angles through the four-point light source three-dimensional detection system; the four-point light source three-dimensional detection system in the step S1 uses a red light type point light source, and calculates each image in the step S2 The corresponding light source direction adopts the highlight black ball calibration method.

[0024] S2. Calculate the light source direction corresponding to each image;

[0025] S3, restore the curvature image of object surface by gradient information; The specific process of described step S3 is: S31, define N as the normal vector of a point on the sphere su...

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 discloses a metal surface fine defect detection method based on vision. The metal surface fine defect detection method comprises the following steps that S1, collecting four to-be-detected metal surface images with different illumination angles through a four-point light source three-dimensional detection system; S2, calculating a light source direction corresponding to each image; S3, restoring the curvature image of the surface of the object through the gradient information; S4, performing preprocessing operation of gray scale transformation and mean filtering on the curvatureimage in sequence; S5, performing threshold segmentation on the preprocessed image by using an automatic threshold segmentation method; S6, removing misjudged pixel points and tolerable fine defects through the area characteristics, and judging whether the product has defects or not; And S7, extracting the texture features of the defects, and classifying the products with the defects through pattern recognition. The defect that in the prior art, the metal surface defect detection omission ratio is high is overcome, and the purposes of rapidly identifying defective products and efficiently classifying the products are achieved.

Description

technical field [0001] The invention relates to the technical field of computer vision, and more specifically, to a vision-based detection method for fine defects on metal surfaces. Background technique [0002] At present, the automatic detection technology for fine defects on the polished metal surface is relatively immature, the missed detection rate and false detection rate of fine defects are high, and the detection efficiency is low. It mainly relies on manual detection and identification of fine defects. Chinese patent "CN102830123B" discloses an online detection method for tiny defects on the surface of metal strips. This patent separates R, G, and B channel images from the color images collected by the camera, corresponding to the reflected light of red, green, and blue light sources respectively. Intensity distribution, the designed surface inclination calculation method, can calculate the surface inclination distribution map through the R channel image and B chann...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/62G06T7/11G06T7/136G01N21/88
CPCG06T7/0004G06T7/11G06T7/136G06T7/62G01N21/8851G01N2021/8887G06T2207/30108G06T2207/10004G06T2207/10024G06T2207/20024
Inventor 李澄非吉登清潘海欣
Owner WUYI 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