Supercharge Your Innovation With Domain-Expert AI Agents!

Machine vision defect detection method and system

A machine vision, defect detection technology, applied in the field of defect detection, can solve problems such as difficulty in obtaining detection results, accurate detection of parts, and changes in the shape of dimensional defects.

Inactive Publication Date: 2020-11-17
SHANGHAI BETTERWAY AUTOMATION CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is to provide a machine vision defect detection method and its system to solve the problem that it is difficult for the existing system to obtain better results when faced with parts with complex surfaces, size defects, shape changes and complex features during the detection process. The problem that the detection effect and manual detection cannot accurately detect the parts

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 defect detection method and system
  • Machine vision defect detection method and system
  • Machine vision defect detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] see figure 1 , the present invention provides a kind of machine vision defect detection method, comprises the following steps,

[0028] Step S1: providing the parts to be tested;

[0029] Step S2: Obtain the coordinates of each part of the part to be measured;

[0030] Step S3: Obtain the three-dimensional data and surface feature data of the part according to the coordinates of each part of the part to be measured;

[0031] Step S4: Generate a realistic three-dimensional data model based on the three-dimensional data and surface feature data of the part to be tested, and perform high-dimensional data expression and defect detection on the part to be tested.

[0032] In this embodiment, by obtaining the coordinates of each part of the part, analyzing the coordinates of each part of the part, and obtaining the three-dimensional data and surface feature data of the part according to the coordinates of each part of the part, by analyzing the three-dimensional data and su...

Embodiment 2

[0034] see Figure 2-3 , the present invention provides a machine vision defect detection system, including a calibration unit, a single-view measurement unit and a global data fusion unit,

[0035] The calibration unit is used to obtain the coordinates of each part of the part to be tested;

[0036] The single-view point measurement unit is used to analyze the coordinates of each part of the part and generate three-dimensional data and surface feature data;

[0037] The global data fusion unit generates a realistic three-dimensional data model through a data fusion formula according to the three-dimensional data and surface feature data of the part, and detects defects on the part.

[0038] In this embodiment, the coordinates of each part of the part to be measured are obtained by setting the calibration unit, and the coordinate data of each part of the part to be measured is transmitted to the single-viewpoint measurement unit, and the single-viewpoint measurement unit perf...

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 machine vision defect detection method and system, and the method comprises the following steps: providing a to-be-detected part, obtaining the coordinates of all parts of the to-be-detected part, and obtaining the three-dimensional data and surface feature data of the part according to the coordinates of all parts of the to-be-detected part, generating a realistic three-dimensional data model according to the three-dimensional data and the surface feature data of the to-be-detected part, and performing high-dimensional data expression and defect detection on the to-be-detected part; acquiring coordinates of each part of a to-be-measured part, acquiring three-dimensional data and surface feature data of the to-be-measured part according to coordinate data of eachpart of the to-be-measured part, and performing data fusion on the three-dimensional data and the surface feature data of the part to acquire a realistic three-dimensional data model; and then high-dimensional data expression and defect detection are performed on the part according to the realistic three-dimensional data model, so that the problems that an existing defect detection device is difficult to detect a complex part and the part cannot be accurately detected during manual detection are solved.

Description

technical field [0001] The invention belongs to the field of defect detection, and in particular relates to a machine vision defect detection method and system thereof. Background technique [0002] Modern process automation production involves a variety of inspection, production monitoring and parts identification applications, such as dimensional inspection for batch processing of auto parts and integrity inspection for automatic assembly, automatic positioning of components for electronic transfer wiring, and automatic positioning of components on ICs. Character recognition, etc., usually this kind of highly repetitive and intelligent work is done by the naked eye, but in some special cases, such as accurate and fast measurement of tiny sizes, shape matching and color recognition, etc., relying on the naked eye Unable to proceed stably. [0003] At present, the main defect detection equipment at home and abroad is composed of 2D cameras combined with customized light sou...

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): G01N21/88G01B11/00
CPCG01B11/002G01N21/8851
Inventor 卢兴中陈红光赵强傅之成
Owner SHANGHAI BETTERWAY AUTOMATION CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com