Supercharge Your Innovation With Domain-Expert AI Agents!

Surface defect detection method and device based on machine learning

A defect detection and machine learning technology, applied in the computer field, can solve problems such as inaccurate detection results, and achieve the effect of solving inaccurate detection results and accurate detection results

Active Publication Date: 2020-07-14
合肥欣奕华智能机器股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a surface defect detection method and device to solve the technical problem in the prior art that only relying on equipment standards to detect product surface defects has inaccurate detection results

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
  • Surface defect detection method and device based on machine learning
  • Surface defect detection method and device based on machine learning
  • Surface defect detection method and device based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] The surface defect detection method in this embodiment includes such as figure 1 Steps shown:

[0061] Step 101: Collect testing samples corresponding to N testing personnel, the testing samples include P defect parameters corresponding to the P historical testing objects one-to-one when the corresponding testing personnel determine that there are no surface defects in the P historical testing objects, And when the corresponding inspector determines that there are surface defects in the Q historical inspection objects, there are Q defect parameters corresponding to the Q historical inspection objects one-to-one.

[0062] Specifically, in this embodiment, test samples corresponding to N quality inspection testers can be collected, the value of N can be configured according to actual needs, and N testers can also be specified in advance, for example: N is 3, and Among the multiple quality inspectors, the historical test results corresponding to the three inspectors A, B,...

Embodiment 2

[0105] Please refer to figure 2 , based on the same inventive concept as the surface defect detection method in Embodiment 1, a surface defect detection device is provided in this embodiment, including:

[0106] The sample collection module 201 is used to collect test samples corresponding to N test personnel, and the test samples include the P values ​​corresponding to the P historical test objects when the corresponding test personnel determine that there are no surface defects in the P historical test objects. defect parameters, and Q defect parameters corresponding to the Q historical detection objects one-to-one when the corresponding inspector determines that there are surface defects in the Q historical detection objects;

[0107] A machine learning module 202, configured to perform machine learning on the detection samples to determine a detection model;

[0108] The image analysis module 203 is configured to perform image analysis on the surface image of the target ...

Embodiment 3

[0122] Based on the same inventive concept, this embodiment provides a device. For the specific implementation of the device, please refer to the description of the first embodiment, and the repeated parts will not be repeated, as image 3 As shown, the device mainly includes a processor 301, a memory 302 and a transceiver 303, wherein the transceiver 303 receives and sends data under the control of the processor 301, and the memory 302 stores a preset program, and the processor 301 reads The program in memory 302 executes the following process according to the program:

[0123] The processor 301 collects testing samples corresponding to N testing personnel, and the testing samples include P defect parameters corresponding to the P historical testing objects one-to-one when the corresponding testing personnel determine that there are no surface defects in the P historical testing objects, And when the corresponding inspectors determine that there are surface defects in the Q h...

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 surface defect detection method and a device based on machine learning, which are used for solving the technical problem of inaccurate detection results caused by the mode ofdetecting the surface defects of products only relying on the standards of equipment in the prior art. The method comprises the following steps of: collecting detection samples corresponding to N detection personnel; carrying out machine learning on the detection sample to determine a detection model; carrying out image analysis on the surface image of the target detection object to obtain defectparameters corresponding to the target detection object; the defect parameter being inputted into the detection model, and the detection result being outputted through the detection model, and the detection result being used to indicate whether the surface of the target detection object is defective or not.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a surface defect detection method and device. Background technique [0002] With the development of computer technology, artificial intelligence and other science and technology, surface defect detection technology based on machine vision technology has emerged. The emergence of this technology has greatly improved the efficiency of production operations, avoided the impact of operating conditions, subjective judgments, etc. on the accuracy of test results, and achieved better and more accurate surface defect detection, and more rapid identification of product surface defects. . [0003] Product surface defect detection is a kind of machine vision technology, which is to use computer vision to simulate the function of human vision, to collect and calculate images of specific objects, and finally to carry out actual detection, control and application. Product surface...

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): G06T7/00G01N21/88G01N21/95G06N20/00
CPCG01N21/8851G01N21/95G01N2021/8883G01N2021/8887G06T7/0002G06T2207/20081
Inventor 朱家兵
Owner 合肥欣奕华智能机器股份有限公司
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