Crack extraction method based on iterative phase consistency and application

An extraction method and consistent technology, applied in image data processing, instruments, calculations, etc., can solve problems such as slow calculation speed, difficulty in selecting image thresholds, difficulty in meeting real-time application requirements, etc., and achieve small calculation and extraction fast effect

Active Publication Date: 2018-08-03
CAPITAL NORMAL UNIVERSITY
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is still difficult to select the threshold for the image enhanced by this method.
Through the search, we found a new crack extraction method (RORPO), which is based on the path opening operation of direction sorting. This process is relatively insensitive to the gray level difference of the image, so it is easier to select the threshold value of the enhanced image, but The only disadvantage is that the calculation speed of this method is relatively slow, and it is difficult to meet the real-time application requirements

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
  • Crack extraction method based on iterative phase consistency and application
  • Crack extraction method based on iterative phase consistency and application
  • Crack extraction method based on iterative phase consistency and application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] A crack extraction method based on iterative phase consistency, the specific steps are as follows:

[0056] ⑴Combine morphological operations and denoising algorithms to preprocess CT images to reduce the influence of background and noise on images;

[0057] (2) Perform polar coordinate transformation on the preprocessed image to obtain the image PolarImg;

[0058] (3) iteratively calculate the phase consistency of the image PolarImg in the polar coordinate system, and enhance the image;

[0059] (4) Perform polar coordinate inverse transformation on the enhanced image;

[0060] (5) According to the unimodal thresholding algorithm, the threshold value of the enhanced image is automatically selected, and then the enhanced image is segmented by 1.5 times of the threshold value to obtain the cracks in the image.

[0061] Preferably, the specific steps of said step (1) are as follows:

[0062] Use the non-local mean algorithm to denoise the original CT image;

[0063] U...

Embodiment 2

[0095] A crack extraction method based on iterative phase consistency, the method for CT images of cylindrical workpieces such as figure 1 , figure 2 Cracks are automatically extracted as shown.

[0096] Proceed as follows:

[0097] S0 combines the bottom hat transformation and denoising algorithm to preprocess the CT image to reduce the influence of background and noise on the image;

[0098] S1 performs polar coordinate transformation on the preprocessed image to obtain the image PolarImg;

[0099] S2 iteratively calculates the phase consistency of the image PolarImg in the polar coordinate system, and enhances the image;

[0100] S3 performs polar coordinate inverse transformation on the enhanced image;

[0101] S4 selects an appropriate threshold for the enhanced image, and then extracts the cracks in the image by threshold segmentation such as Figure 9 , Figure 10 shown.

[0102] The more specific steps of S2 are as follows:

[0103] Use PolarImg to represent t...

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 a crack extraction method based on iterative phase consistency. The method comprises the specific steps that (1) a CT image is preprocessed by combining morphological operation and a denoising algorithm; (2) polar coordinate transformation is carried out on the preprocessed image to acquire the image PolarImg; (3) the phase consistency of the image PolarImg is iterativelycalculated in a polar coordinate system, and the image is enhanced; (4) polar coordinate inverse transformation is carried out on the enhanced image; and (5) the method automatically selects a threshold for the enhanced image according to a unimodal thresholding algorithm, and then the enhanced image is split by 1.5 times the threshold to acquire a crack in the image. The method can automaticallydetect the high-precision crack from the CT image of an industrial part, and is not affected by the gray contrast difference of the CT image. In addition, the method has the advantages of small calculation amount and fast extraction speed, and can meet real-time application requirements.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a crack extraction method and application based on iterative phase consistency, which can be applied to defect detection of industrial parts. Background technique [0002] With the development of computed tomography technology, non-destructive testing technology is more and more widely used in industrial production. The detection and analysis of workpiece defects plays a very important role in quality and safety control. On the one hand, information such as the shape and size of workpiece defects directly reflects the influence of relevant factors in the processing process. Quantitative analysis and research on this information will help to improve and develop production processes; , analyzing the trend of defect discovery can help predict the service performance and service life of the workpiece or equipment. Cracks are one of the common defects in industrial ...

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): G06T7/00G06T7/136G06T5/00G06T5/10
CPCG06T5/002G06T5/10G06T7/0004G06T2207/10081G06T2207/30164G06T7/136
Inventor 李宏伟邓小娟
Owner CAPITAL NORMAL UNIVERSITY
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