A Copper Strip Surface Defect Detection Method Based on Online Sequence Extreme Learning Machine

A technology of sequence limit and defect detection, which is applied to computer parts, instruments, character and pattern recognition, etc., to achieve the effect of reducing noise and reducing influence

Active Publication Date: 2016-07-06
ZHEJIANG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing computational vision technology in the detection method of copper strip surface defects, the present invention proposes a copper strip surface defect detection method based on an online sequence extreme learning 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 Copper Strip Surface Defect Detection Method Based on Online Sequence Extreme Learning Machine
  • A Copper Strip Surface Defect Detection Method Based on Online Sequence Extreme Learning Machine
  • A Copper Strip Surface Defect Detection Method Based on Online Sequence Extreme Learning Machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0107] like figure 1 As shown, the flow chart of the copper strip surface defect detection method of the present invention. First, the image of the surface of the copper strip is acquired through the image acquisition module. Due to the existence of image noise, the subsequent processing effect is affected. It is necessary to denoise and enhance the surface image first. At the same time, in order to reduce the influence of uneven illumination, the surface image Perform top-hat transformation processing. In actual production, the probability of defects on the surface of copper strips is about 5%. Therefore, it is necessary to reduce the amount of calculation and improve the real-time performance of the system through the pre-inspection of surface defect images. Segment the image with surface defects, segment the defects in the surface image, and then extract some geometric and texture features of each defect. Through the trained classifier, the type of surface defect can be i...

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 copper strip surface defect detection method based on the online sequence extreme learning machine includes the following steps: acquiring the image of the copper strip surface through the image acquisition module; using the median filter method with a mask size of 7×7 to analyze the collected copper strip surface image Carry out enhancement to reduce the contained noise and reduce the impact of noise on the surface image quality; perform top-hat transformation processing on the surface image of the copper strip to reduce the influence of uneven illumination; adopt the copper strip surface image pre-check based on the 8-neighborhood difference Methods: For the surface image of the copper strip that is judged to have surface defects after pre-inspection, an image segmentation method is used to segment the defects in the surface image; the geometry, grayscale, shape, texture and other characteristics of each defect are extracted, and the principal components are used to The analysis method optimizes the feature dimension of the copper strip surface defect and reduces the dimensionality; designs a copper strip surface defect classifier based on an online sequence extreme learning machine, and uses samples for training; extracts the features of the surface image of the copper strip to be detected, and identifies the surface The type of defect.

Description

technical field [0001] This patent relates to a method for detecting surface defects of copper strips by using computer vision technology. Background technique [0002] In my country, copper strip is an important variety of copper processing materials, which are widely used in electronic communications, machinery manufacturing, aerospace industry and other fields. In recent years, with the development of modern electronics, communications and semiconductor industries, the demand for low-end copper strip products has gradually shrunk, followed by the increasing demand for high-end products, and then a special proposal for the quality of copper strips The requirements of "precision copper strips" are met, that is, the copper strips have the quality requirements of "high surface, high performance and high precision". The surface quality of copper strip is an important indicator to determine the quality of its products. Due to the influence of factors such as production equipm...

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): G06K9/54G06K9/66
Inventor 高飞胡伟江张元鸣陆佳炜毛家发梅凯城李征肖刚
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap