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

Gamma photon image super-resolution image enhancement method based on digital twinning

A high-resolution image, low-resolution image technology, applied in the field of industrial inspection applications, can solve problems such as the inability to adapt to the actual inspection characteristics of industrial complex parts, the technical stability requirements of industrial inspection applications, and the inability to meet the requirements of super-resolution image quality. , to achieve the effect of non-destructive resolution detection, improving the fineness of the image, and increasing the details of the image

Pending Publication Date: 2021-10-22
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current mainstream research methods all use the method of algebraic geometry for modeling, which can solve certain problems. However, the conventional super-resolution image enhancement method has great limitations on the enhancement effect, although the original blurred image has been improved. clarity, but still cannot meet the requirements of academia and industry for super-resolution image quality
In particular, the existing image enhancement methods can no longer adapt to the actual detection characteristics of industrial complex parts and the technical stability requirements of industrial detection applications

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
  • Gamma photon image super-resolution image enhancement method based on digital twinning
  • Gamma photon image super-resolution image enhancement method based on digital twinning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and examples of implementation.

[0034] as attached figure 1 Shown, is the schematic flow chart of the training model based on deep neural network of the present invention, specifically comprises the following steps:

[0035] Step 1-1: as attached figure 1 As shown, low-resolution images are preprocessed before image super-resolution enhancement. The low-resolution image is input to a standardized convolutional layer with a convolution kernel size of 1×1, the number of input layers is 3, and the number of output layers is 3 convolutional layers, so that the parameters of this layer remain unchanged during the training process. to normalize the image.

[0036] Step 1-2: Input the normalized image to the convolutional layer whose convolution kernel size is 3×3, the number of input channels is 3, and the number of output channels is 256. figu...

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 gamma photon image super-resolution image enhancement method based on digital twinning, and the method comprises the steps: firstly designing a network structure of a deep neural network, then providing a large number of image samples for network training according to the designed network structure, wherein the network training process is composed of feature extraction, nonlinear mapping and up-sampling reconstruction. The loss between a super-resolution reconstructed image and a real high-resolution image is continuously reduced through an optimizer with a specified learning rate, and the method can adapt to actual detection characteristics of industrial complex parts and technical stability requirements of industrial detection image application.

Description

technical field [0001] The invention relates to the field of industrial detection applications, in particular to a method for super-resolution image enhancement of gamma photon images for detection of cavity structures and inner wall defects of complex pieces of aviation industry equipment. Background technique [0002] In the aviation propulsion system, complex parts of industrial equipment such as engine parts and tail nozzle aerodynamic flow channels have high material density and complex inner cavity structure. The non-destructive testing of the inner cavity structure and inner wall defects has become an urgent problem in the testing field. Conventional detection methods are limited by factors such as the material density of complex parts and the complexity of the inner cavity structure, and cannot achieve undisturbed and non-destructive high-resolution detection. [0003] The main methods currently used in the academic community are: interpolation-based super-resolution...

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
IPC IPC(8): G06T3/40G06T5/00G06K9/46G06N3/04G06N3/08
CPCG06T3/4053G06N3/08G06T2207/20081G06N3/045G06T5/73
Inventor 范兼睿刘小姣徐风友汪玥张昕婷沈高青曹盼颜孟凡鲍育泓
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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