Defect characteristic extraction and identification method of AOI system used for bullet apparent defect detection

A technology for defect detection and identification methods, used in character and pattern recognition, optical testing flaws/defects, instruments, etc.

Inactive Publication Date: 2014-10-22
NINGBO MOSHI OPTOELECTRONICS TECH
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, there is no application of the AOI system for the detection of apparent defects of bullets. Although the image of the object under test is obtained optically, and the digital image of the object under test is obtained by using a sensor, after the image is processed Comparing, analyzing, and judging are the basic principles of AOI technology, but how to extract defect features and identify them in the detection of bullet apparent defects is still a blank in technology

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
  • Defect characteristic extraction and identification method of AOI system used for bullet apparent defect detection
  • Defect characteristic extraction and identification method of AOI system used for bullet apparent defect detection
  • Defect characteristic extraction and identification method of AOI system used for bullet apparent defect detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] The defect feature extraction and recognition method of the AOI system for the detection of apparent defects of bullets includes the following steps:

[0036] (1) Obtain the surface image of the bullet through the AOI system, and then obtain the connected domain mark image;

[0037] (2) Preset the known defect types to be inspected according to the expectations of the bullet apparent defect detection, and obtain the image characteristics required to determine each defect;

[0038] (3) Associate all required image features with the parameters of the connected domain labeled image, convert them into corresponding general formulas, and preset standard thresholds for image features;

[0039] (4) Perform image feature calculation for each connected domain on the connected domain label image, compare the result with a standard threshold, and determine the type of defect.

[0040] Wherein, in the step (1), a region growing method or a labeling algorithm is adopted to obtain the connecte...

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 defect characteristic extraction and identification method of an AOI system used for bullet apparent defect detection. The method includes the following steps: (1) obtaining a bullet surface image through the AOI system and obtaining a connection domain mark image through the bullet surface image; (2)according to expectation, presetting to-be-detected known defect types and obtaining image characteristics needed in judgment of each kind of defect; (3) associating all needed image characteristics with parameters of the connection domain mark image so as to obtain a corresponding calculation general formula through conversion and presetting standard thresholds of the image characteristics; (4) carrying out image characteristic calculation on each connection domain of the connection domain mark image and comparing the results with the standard thresholds so as to determine a defect type. Through analysis of a pullet structure and apparent defects of the bullet structure, the method designs the image characteristics of different kinds of defects in a targeted manner when the AOI system is used to detect the apparent defects and carries out datamation of the image characteristics and then comparative judgment of image processing data is combined so that an effective and comprehensive defect result is obtained and a technical blank in the field is filled.

Description

Technical field [0001] The present invention relates to the field of image feature extraction and recognition, in particular to a defect feature extraction and recognition method of an AOI system used for bullet apparent defect detection. Background technique [0002] AOI (Automatic Optic Inspection), also known as automatic optical inspection, is based on motion machine vision as a basic technology, as a way to improve the shortcomings of traditional manual optical instruments for inspection, and to improve the accuracy and speed of optical image inspection systems. technology. [0003] In the prior art, there is no application of the AOI system for the detection of the apparent defect of the bullet. Although the image of the measured object is obtained optically, and the digital image of the measured object is acquired by the sensor, after the image is processed Comparing, analyzing and judging are the basic principles of AOI technology, but how to extract and identify defect fe...

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): G06K9/00G06K9/46G01N21/88
Inventor 杨雷尹志强赵泽东陈仕隆吕坤
Owner NINGBO MOSHI OPTOELECTRONICS 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