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

Multi-scale image contrast enhancement method for pipeline welding seam detection

A welding seam detection and image comparison technology is applied in the field of multi-scale image contrast enhancement for pipeline weld inspection, which can solve problems such as dark X-ray digital imaging, and achieve the effects of improving quality, improving detection accuracy, and improving local clarity.

Inactive Publication Date: 2017-06-13
四川迪派锐科技有限公司
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

High-quality digital negatives are helpful for professional technicians to quickly and effectively judge whether there are defects, but for pipeline welds, the weld joint part of the pipe wall is thicker than other parts, which makes the X-ray digital imaging of the weld darker. Defective Judgment

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
  • Multi-scale image contrast enhancement method for pipeline welding seam detection
  • Multi-scale image contrast enhancement method for pipeline welding seam detection
  • Multi-scale image contrast enhancement method for pipeline welding seam detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The original X-ray image of the pipeline weld is attached Figure 11 As shown, the multi-scale image contrast enhancement method of the present invention is used for processing, and the steps are as follows figure 1 As shown, the specific description is as follows:

[0041] S01, image preprocessing is performed on the original image, the steps are as follows figure 2 As shown, specifically:

[0042] s011. Data type conversion: convert the bitmap data of the original image into double-precision data;

[0043] s012. Logarithmic transformation: expand the low gray value part and compress the high gray value part to achieve the purpose of emphasizing the low gray value part;

[0044] s013. Median filtering: smoothing impulse noise, such as abnormal pixels on a flat panel detector;

[0045] s014. Image grayscale normalization: weaken the influence of different X-ray intensities or directions on subsequent image processing;

[0046] S02. Decompose the preprocessed image...

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 multi-scale image contrast enhancement method for pipeline welding seam detection. The method comprises the following steps of performing preprocessing including data type conversion, logarithmic transformation, median filtering and image grayscale normalization; performing image decomposition including down-sampling, up-sampling and detailed image calculation; and performing image reconstruction: performing up-sampling, performing detail enhancement processing on bL-1, adopting an exponential function y=ax / x / p-1 as an enhancement function, and performing detail enhancement to obtain yL-1; performing addition, continuing to perform up-sampling, repeating the process until y0 after b0 detail enhancement is added, and obtaining a reconstructed image, so that multi-scale image contrast enhancement is finished. According to the method, a pipeline welding seam X-ray image can be enhanced, so that a welding seam part is made clear, expression of detail defects such as bubbles, cracks, slag inclusion and the like is facilitated, and detection accuracy is improved.

Description

technical field [0001] The invention relates to pipeline weld detection, in particular to a multi-scale image contrast enhancement method for pipeline weld detection. Background technique [0002] Pipelines are widely used in industrial production, pipeline transportation, national defense construction, etc., and the quality inspection of pipeline welds is an indispensable link in pipeline welding production. Pipeline welding quality inspection mainly includes two aspects: appearance inspection and internal inspection. Appearance inspection mainly detects the outline size of weld seam and appearance defects such as weld bead and undercut, and can carry out preliminary quality screening for the produced pipeline. However, the appearance inspection cannot detect the internal defects of the weld, such as air bubbles, cracks, slag inclusions, etc. X-ray digital imaging is the most commonly used method for internal inspection of welds. Through the analysis and processing of dig...

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): G06T5/00
CPCG06T2207/10116G06T5/73
Inventor 李运键徐浩刘长山李诗武胡道未袁蓉姜小容
Owner 四川迪派锐科技有限公司
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

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