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

Magnetic sheet surface defect detection method based on convolution neural network

A convolutional neural network and defect detection technology, applied in the field of surface defect detection, can solve problems such as the decline in recognition rate, achieve the effects of enhancing detection accuracy, high robustness, and improving poor training

Active Publication Date: 2018-05-25
ZHEJIANG UNIV OF TECH
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The recognition speed of defect features will also be greatly improved, but this type of method requires a large number of samples to train to achieve a high recognition rate, and too few training samples may lead to a decline in the recognition rate

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
  • Magnetic sheet surface defect detection method based on convolution neural network
  • Magnetic sheet surface defect detection method based on convolution neural network
  • Magnetic sheet surface defect detection method based on convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.

[0037] refer to Figure 1 ~ Figure 4 , a disk defect detection method based on convolutional neural network, including the following process: firstly collect training materials, there are 1000 disks with defects and 500 disks without defects. The top view of both sides of the magnetic sheet is collected under standard environment, by figure 2 In the image preprocessing process shown in the figure, the magnetic disk image is first grayscaled, and the grayscale image is subjected to Hough circle transformation to detect the outer contour of the magnetic disk, and the smallest circumscribed square of the circle is cut according to the center and radius of the circle; and then The cut square image is used as a template, and batch template matching processes the remaining images so tha...

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 magnetic sheet surface defect detection method based on a convolution neural network, and the method comprises the following steps: 1, obtaining a top-view image of a to-be-detected magnetic sheet, and carrying out the preprocessing of the image: gray processing, Hough-circle transform, size conversion, and rotating cutting; 2, inputting the preprocessed image into a pre-trained convolution neural network for defect detection, detecting whether the surface of the magnetic sheet has defects or not, and carrying out the classification of defects; carrying out the feature extraction of the image through an input layer, a convolution layer, a sampling layer and a full-connection layer of the convolution neural network, wherein the defect classification of the extracted features is carried out through a Softmax classifier. Compared with the prior art, the method is high in detection precision, and is better in robustness.

Description

technical field [0001] The invention belongs to surface defect detection technology, in particular to a method for detecting surface defects of a magnetic sheet based on a convolutional neural network. Background technique [0002] With the rapid development of electronic technology and computer technology, digital image processing technology has been widely used in many industries and fields, such as medical image processing and analysis, industrial control and detection, due to its advantages of large information content, intuitive expression, convenient transmission and storage, etc. Automation, aerospace remote sensing mapping, etc. With the improvement of my country's national economic level, people's demand for high-quality, high-precision, and high-reliability products is also increasing. The ensuing problem is how to detect and judge whether the mass-produced products meet the performance indicators. [0003] The traditional detection method is to detect manually. 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 Applications(China)
IPC IPC(8): G06T7/00G06N3/04
CPCG06T7/0004G06T2207/20084G06T2207/20081G06N3/048G06N3/045
Inventor 姚明海胡涛顾勤龙
Owner ZHEJIANG 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