Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Defect Detection Algorithm for Industrial Parts Based on Pixel-Vector Invariant Relation Features

A detection algorithm and pixel technology, applied in computer parts, computing, image analysis, etc., to achieve high detection rate

Active Publication Date: 2021-08-10
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when there are different scales in the size of the defect or the position of the part under test has a random angular offset between the position of the field of view and the template, how to define this measurement difference will be a difficult problem to solve

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 Defect Detection Algorithm for Industrial Parts Based on Pixel-Vector Invariant Relation Features
  • A Defect Detection Algorithm for Industrial Parts Based on Pixel-Vector Invariant Relation Features
  • A Defect Detection Algorithm for Industrial Parts Based on Pixel-Vector Invariant Relation Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be further described in detail below in conjunction with the accompanying drawings and examples of implementation.

[0075] The implementation of a part defect detection algorithm based on pixel vector invariant relationship features mainly includes three steps: 1. Extraction of edge pixels to be detected. 2. Pixel vector extraction. 3. Pixel vector invariant feature definition and matching. Its specific algorithm process is realized as figure 1 shown.

[0076] 1. Extraction of edge pixels to be detected

[0077] Such as figure 2 As shown, firstly, select an appropriate gradient threshold, and use the Canny edge detection algorithm to realize the defect region of interest (such as figure 2 The edge detection of (a)) obtains the binary image of all edge pixel connected domains in the region of interest, such as figure 2 (b). Then filter the extracted edge connected domain contour according to the contour position, and extract the cont...

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 relates to an industrial part defect detection algorithm based on pixel vector invariant relation features. It includes the following steps: Step 1: Extract the contour of the contour or local texture to be detected to obtain the edge pixels to be detected; Step 2: Define the width of the detection window, and optimize and adjust the width of the detection window according to the defined pixel linear relationship judgment function to realize Extract the direction vector between pixels in the window; slide the detection window along the edge to be detected with a preset step size, and complete the extraction of all edge pixel vectors to be detected; Step 3: Calculate the invariant relationship feature of the edge pixel vector to be detected, and the standard The features of the invariant relationship between the edge pixels of the part are compared to determine whether the part is defective or not. The invention can use the difference in the local position relationship of the contour pixels to construct the edge pixel vector, and use the invariant information between the vector direction or the vector modulus to carry out the difference matching to realize the defect detection.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and automation, and in particular relates to an industrial part defect detection algorithm based on pixel vector invariant relationship features. Background technique [0002] With the development of science and technology, the automation of production process and the wide application of mechanical processing, the requirements for the precision, quality and processing efficiency of production and processing parts are constantly increasing. At the same time, the defect detection of parts has attracted more and more attention. Part defect detection is an important means to ensure the safety of parts. The traditional part damage detection method mainly relies on manual identification, which has the disadvantages of slow speed, troublesome data recording, and easy visual fatigue of the inspector. Moreover, the detection results are subjective, and it is difficult to guarantee the accuracy...

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): G06T7/13G06T7/181G06T7/40G06T7/00G06K9/46
CPCG06T7/0002G06T7/13G06T7/181G06T7/40G06V10/44
Inventor 华春生马立永何玉庆
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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
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