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

Cell neural network hot region fusion method based on wavelet transform

A neural network and wavelet transform technology, applied in the field of image processing, can solve the problems of not using the high and low frequency characteristics of thermal images, and achieve the effect of enhancing defect features, good effect, and enhancing edges and contours

Active Publication Date: 2018-11-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the effects of these algorithms have limitations and do not take advantage of the high and low frequency characteristics of thermal images

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
  • Cell neural network hot region fusion method based on wavelet transform
  • Cell neural network hot region fusion method based on wavelet transform
  • Cell neural network hot region fusion method based on wavelet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] figure 1 It is a flow chart of the fusion method of cellular neural network thermal region based on wavelet transform in the present invention.

[0043] In this example, if figure 1 As shown, a kind of wavelet transform-based cellular neural network thermal region fusion method of the present invention mainly includes the following three steps:

[0044] S1. Use ICA algorithm (Independent Component Analysis algorithm, Independent Component Analysis) to adopt three different comparison functions G k (x) Calculating uncorrelated thermal region images UR1, UR2 and UR3 to obtain thermal region image UR1 k , UR2 k , UR3 k ; Wherein, k=1,2,3, three different comparison functions are specifically

[0045]

[0046] Through a variety of comparison functions, multi-source information can be obtained, making the information richer and providing more useful data for data fusion.

[0047] In this example, according to figure 2 The eddy current thermal imaging detection sys...

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 cell neural network hot region fusion method based on wavelet transform. The method comprises a step of calculating uncorrelated hot region images by using different contrastfunctions by using an ICA algorithm to obtain various forms of hot region images, a step of extracting low-frequency hot region images from the various forms of hot region images by using the wavelettransform, and a step of fusing the low-frequency hot region images based on a cellular neural network. In this way, defect features in the images are enhanced, the edges and contours of thermal images are enhanced, and thus the visualization effect of defect detection is better and more accurate.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a wavelet transform-based cell neural network thermal region fusion method. Background technique [0002] In eddy current thermography testing, the thermal response curves of the defect area and the non-defect area of ​​the specimen are weakly correlated. Therefore, the infrared thermal images of defect areas and non-defect areas can be separated based on ICA algorithm. Due to the different contrast functions used when using the ICA algorithm, different thermal separation regions can be obtained. These thermally separated regions have their own advantages and disadvantages in representing defects, thus requiring a method to fuse images of different thermal regions. [0003] In the prior art, scholars respectively proposed thermal region image fusion algorithms based on genetic algorithm, wavelet transform and Contourlet. However, the effects of these a...

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): G06T5/50
CPCG06T5/50G06T2207/20064G06T2207/20084G06T2207/20221
Inventor 程玉华殷春甘文东黄雪刚陈晓辉巩德兴张昊楠
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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