Sheet metal surface anomaly detection method based on image analysis

A metal plate and anomaly detection technology, applied in image analysis, image data processing, optical testing flaws/defects, etc., can solve the problems of incomplete detection, low confidence, lack of quantification, etc., and achieve the goal of improving accuracy and real-time Effect

Active Publication Date: 2017-10-24
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the above-mentioned related detection requirements, manual detection has been difficult to meet, and there are shortcomings such as incomplete detection, low confidence, lack of quantification, and high labor intensity.

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
  • Sheet metal surface anomaly detection method based on image analysis
  • Sheet metal surface anomaly detection method based on image analysis
  • Sheet metal surface anomaly detection method based on image analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0069] figure 1 It is a flowchart of a method for detecting anomalies on the surface of metal sheets based on image analysis.

[0070] In this example, if figure 1 As shown, the present invention is a kind of metal plate surface anomaly detection method based on image analysis, comprises the following steps:

[0071] S1. Calculate the integral image of the entire image to be detected

[0072] For an image I to be detected, such as figure 2 As shown, when many rectangles need to be summed for all the pixels in each rectangle, if a separate calculation is performed for each rectangle, obviously there will be a lot of repeated calculations. Therefore, we use the following The formula can be iterated to calculate the integral map of the entire image to be detected

[0073]

[0074] Among them, I(x, y) represents the pixel value at coordinates (x, y), and I′(x, y) represents the sum of pixel values ​​at the upper left corner of the image to be detected at coordinates (x, y)...

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 present invention discloses a sheet metal surface anomaly detection method based on image analysis. The mean value and the variance of an image are employed to perform coarse detection to obtain a suspected anomaly set and a normal set; a compressed sensing principle is employed to perform feature learning of the normal set, the Bayes idea is utilized to perform analysis and determination of the anomaly set so as to realize fine detection of surface anomaly, and therefore the method of combination of the coarse detection and the fine detection is employed to perform rapid detection of surface defects and the accuracy and the timeliness of the detection are improved.

Description

technical field [0001] The invention belongs to the technical field of image processing and detection, and more specifically relates to an image analysis-based method for detecting abnormalities on the surface of metal plates. Background technique [0002] Surface anomaly (or defect) detection of sheet metal is an important part of its production process, and detection of surface anomalies of sheet metal products (or buildings) is also a necessary means for daily inspection or maintenance in related fields. Whether there is any abnormality on the surface of the metal sheet and its building body and the size of the abnormal part will have a very important impact on the quality or safety of related products. Therefore, in order to ensure the quality of products and the safety of related applications, it is necessary to detect surface abnormalities of related products, so that abnormalities such as stains, scratches, scars, wear, cracks, and rust on the surface can be found in ...

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): G06T7/00G06K9/62G01N21/88G01N21/94
CPCG06T7/0008G01N21/8851G01N21/94G06T2207/30136G06T2207/20021G01N2021/8887G06F18/24155
Inventor 康波陈亮李云霞唐诗甘君钱志敏
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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