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

Small hardware fitting defect detection algorithm based on machine learning

A machine learning and defect detection technology, which is applied in the direction of optical defect/defect, instrument, calculation, etc., can solve the problems of inaccurate defect detection and complicated detection process, and achieve complete removal, fast noise reduction, brightness and color Enhanced effect

Pending Publication Date: 2022-02-25
TIELING POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER COMPANY +2
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above-mentioned patents all introduce the defect detection method of the object under test by means of image recognition, but the detection process is relatively complicated. When detecting defects, problems such as noise and brightness in the image will directly affect the analysis and judgment of object defects, resulting in defects Inaccurate detection

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
  • Small hardware fitting defect detection algorithm based on machine learning
  • Small hardware fitting defect detection algorithm based on machine learning
  • Small hardware fitting defect detection algorithm based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, the embodiment of the present invention provides a machine learning-based small hardware defect detection algorithm, including the following steps:

[0039] Sp1: Image acquisition: select a suitable light source, adjust the distance between the tested fittings and the light source, and collect images of the tested fittings;

[0040] Sp2: Image enhancement: correcting the illumination of the collected image to enhance the collected image;

[0041] Sp3: Image optimization: de-noise the enhanced image, and combine with the 3D block matching algorithm to optimize and de-noise again;

[0042] Sp4: Binarization processing: the processed image is binarized, and the processed image is divided into a spot image and a background image;

[0043] Sp5: mark preservation: compare the detected image with the original image, and carry out mark preservation.

Embodiment 2

[0045] Such as figure 1 As shown, the secondary light tube is the selected light source, and the secondary light tube is composed of 80-120 light-emitting diodes arranged equally. The light-emitting direction of each secondary tube is 120°. position, the industrial digital camera is the image acquisition device of the tested fittings, which collects the images of the tested fittings, evaluates the light component of the collected image, obtains the expression of the light component, and uses the two-dimensional gamma function to perform automatic calculation according to the distribution characteristics of the light. Adaptive adjustment, and the image is processed by image grayscale to increase the value of the value of the image illumination component after the image is collected, I is the collected image, (x, y) is the coordinate of the image pixel, G(x, y, σ) is a Gaussian function, L(x,y,σ) is the scale space of the image, is the convolution operation;

[0046]

[00...

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 small hardware fitting defect detection algorithm based on machine learning, and relates to the technical field of hardware fitting defects. The algorithm comprises the steps of taking a proper light source, adjusting the distance between a detected hardware fitting and the light source, carrying out image collection on the detected hardware fitting, carrying out illumination correction on the collected image to enhance the collected image, carrying out de-noising processing on the enhanced image, carrying out optimization and denoising again by combining a three-dimensional block matching algorithm, carrying out binarization processing on the processed image, dividing the processed image into a light spot image and a background image, comparing a detected image with an original image, and marking and storing. The defect detection precision is improved, the process is simple, a defect part can be visually marked, a detector can conveniently check through a display, and the efficiency of a detection result is improved.

Description

technical field [0001] The invention relates to the technical field of hardware defect detection, in particular to a machine learning-based detection algorithm for small metal defects. Background technique [0002] The patent number is CN202010393940.7, a method and system for detecting defects of transmission line fittings based on cascade target detection, including: using the trained first target detection model to detect the connection area of ​​the transmission line image, and cut the detected connection area come out; use the n connected areas whose area size meets the preset conditions as the image to be recognized; use the trained second target detection model to detect small metal defects on the image to be recognized, and obtain the coordinates of the small metal defect on the image to be recognized; According to the mapping relationship between the coordinates of the image to be recognized and the coordinates of the original image, the defects of small fittings ar...

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): G06V10/20G06V10/28G06V10/30G06V10/74G06K9/62G01N21/88
CPCG01N21/8851G01N2021/8887G06F18/22
Inventor 张永谦高嵩王敏珍倪虹霞李成赵立英
Owner TIELING POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER COMPANY
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