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

Machine vision-based workpiece defect detection method

A defect detection and machine vision technology, which is applied in the direction of optical defect/defect detection, can solve the problems of inability to meet the real-time detection of workpiece surface defects, poor segmentation effect, etc., and achieve effective detection, good adaptability, and high detection accuracy.

Inactive Publication Date: 2019-06-18
TIANJIN POLYTECHNIC UNIV
View PDF9 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has a poor segmentation effect on fine scratches and smaller defects, and cannot meet the real-time detection of workpiece surface defects in the present invention.

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
  • Machine vision-based workpiece defect detection method
  • Machine vision-based workpiece defect detection method
  • Machine vision-based workpiece defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0026] The overall framework flow diagram of the present invention is as figure 1 shown. First, collect the image of the flange plate workpiece, use the Zhang calibration method to calibrate the camera, and then correct the distortion of the workpiece image; then use the Gaussian filter to smooth the image, using a 5×5 Gaussian with a standard deviation of 1 The kernel performs convolution operation to extract the region of interest; the Canny algorithm, Sobel algorithm, Roberts algorithm and Prewitt algorithm are used to detect the pixel-level edge of the image, and the detection results of various algorithms are compared, and the Canny algorithm with the best extraction effect is selected; The sub-pixel edge detection algorithm based on the gray moment extracts the sub-pixel edge of the workpiece image; finally, the circle fitting method is ...

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 provides a machine vision based workpiece defect detection method. According to the method, the image of a flange type workpiece is acquired; a camera is calibrated, and calibration error is obtained; sub-pixel edge information extraction is performed on a workpiece contour; a distance from a fitting edge to the workpiece contour is calculated; whether the distance is larger than a given threshold value is judged through comparison, so that the damage condition of the workpiece contour is determined; and with the problem that the complex surface texture of the workpiece affects the segmentation of the surface scratches and corrosions of the workpiece considered, pixel stratified sampling-based PixelNet convolutional neural network is adopted to segment the surface defects. Results show that the method of the invention can accurately detect the shape defects and surface defects of the workpiece and has improved robustness.

Description

technical field [0001] The invention relates to a workpiece defect detection method based on machine vision, which improves the detection accuracy and detection efficiency when using image processing technology to detect flange plate workpieces. Background technique [0002] Since the 1960s, the operating speed of computers has been significantly improved. At the same time, with the advent of CCD technology, defect detection technology based on machine vision has been widely used in industrial production lines, such as machinery, electronics, printing, and textile industries. With the help of advanced detection technology Improve product quality and production efficiency. As a method of non-destructive testing, machine vision inspection obtains clear images of the object to be tested through line array or area array cameras, and performs image processing by computer to complete real-time detection of target defects. [0003] With the rapid development of my country's manufa...

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
IPC IPC(8): G01N21/88
Inventor 耿磊魏全生肖志涛吴骏张芳李文科刘彦北王雯
Owner TIANJIN POLYTECHNIC 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