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

Core CT image super-resolution reconstruction method based on three-dimensional convolutional neural network

A technology of super-resolution reconstruction and three-dimensional convolution, which is applied in the field of image repair enhancement and core three-dimensional image super-resolution. Effect

Active Publication Date: 2018-11-27
SICHUAN UNIV
View PDF2 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Dong C, Chen C L, He K, etal.(Image Super-Resolution Using Deep Convolutional Networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence 2016,38(2):295-307) Introducing Convolutional Neural Networks to a Single 2D Image In super-resolution reconstruction, but this method is only suitable for two-dimensional image super-resolution, and cannot complete the three-dimensional convolution operation

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
  • Core CT image super-resolution reconstruction method based on three-dimensional convolutional neural network
  • Core CT image super-resolution reconstruction method based on three-dimensional convolutional neural network
  • Core CT image super-resolution reconstruction method based on three-dimensional convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] In order to make the restoration method of the present invention easier to understand and closer to the real application, the following is an overall description of the entire process from the preprocessing of the original core CT training samples to the completion of the CT image super-resolution reconstruction, including the three-dimensional super-resolution of the present invention. Identify how to rebuild the network using:

[0050] (1) Using CT machine to scan the cut small core samples, multiple continuous two-dimensional image sequences can be obtained, which are sequentially read in and stored to generate three-dimensional images. The CT three-dimensional image as figure 1 shown. Extract 400 continuous pictures from it, cut out a 400*400 pixel area for each single two-dimensional picture, and select 10 groups from different types of rock samples according to such rules as the training set and test set. The training set images are as follows: image 3 , 4 , 5...

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 core three-dimensional image super-resolution method, which comprises the following steps: (1) sending an image in a training set to a three-dimensional convolutional neuralnetwork proposed by the method, wherein the first layer of the network performs low-frequency feature extraction; (2) allowing the second to eleventh layers of the network to be responsible for learning a mapping relationship between low frequency and high frequency features; (3) allowing the twelfth layer of the network to use the learned mapping relationship to map the low frequency features into the high frequency features; (4) using a residual learning method to calculate a root mean square error, and accelerating the training by using the momentum gradient descent method; (5) using the adaptive learning rate and a gradient cutting method to optimize the training process during the process of training, and using the training configurations in (1) to (5) to perform continuous iterativetraining; and (6) using the trained network model to complete the reconstruction. The invention can improve the resolution of a rock CT three-dimensional image, restore more structure and details, andprovide clearer image samples for the next step of geology-petroleum research.

Description

technical field [0001] The invention relates to an image restoration and enhancement method, in particular to a rock core three-dimensional image super-resolution method, and belongs to the technical field of three-dimensional image super-resolution reconstruction. Background technique [0002] In the process of petroleum geological analysis, it is usually necessary to obtain a three-dimensional core structure to study the physical properties of rocks, and to analyze the seepage properties and migration laws in rock reservoirs. CT (Computed Tomography, computerized tomography) is a three-dimensional imaging technology that can provide high-quality images of internal structures of objects, and is widely used in medical image diagnosis and geological exploration. However, in production and life, the resolution of CT images is restricted by scanning equipment and actual conditions. Usually, to obtain higher-precision CT images, it takes longer scanning time. Due to the extensi...

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): G06T5/00
CPCG06T2207/20084G06T2207/20081G06T2207/10081G06T5/00Y02T10/40
Inventor 何小海王煜凯滕奇志张廷蓉吴小强王正勇余艳梅
Owner SICHUAN UNIV
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