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

Rock core CT image denoising method based on deep learning

A technology of deep learning and CT images, applied in neural learning methods, image enhancement, image data processing, etc., can solve the problems that the pore structure cannot be accurately described, and the core is difficult to reflect the real situation of the actual core.

Pending Publication Date: 2022-08-05
SOUTHWEST PETROLEUM UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the heterogeneity of the actual core, it is difficult to reflect the real situation of the actual core through the simple two-dimensional CT image and simple algorithm, and cannot accurately describe the complex pore structure inside it.

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
  • Rock core CT image denoising method based on deep learning
  • Rock core CT image denoising method based on deep learning
  • Rock core CT image denoising method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] like figure 1 As shown, this embodiment provides a deep learning-based core CT image denoising method, which includes the following steps:

[0060] 1. Data set preparation; visualize the CT of the core by 3D digitization of the core; add random noise to the core, use the slicing method to obtain a single image of the core, and obtain the standard 128*128 by adding salt and pepper and Gaussian white noise The noise map and the corresponding standard original image, the noise point is marked as 1, the original image is marked as 0, and the complete data set is obtained by grouping by naming; then the data set is divided into training set: test set: validation set = 7 : 2:1, so far, the data preparation phase is completed.

[0061] 2. Model forward inference, pass the noise image into the model, and obtain the output of the forward inference graph;

[0062] The model proceeds as follows:

[0063] a) The format of the input image Imagegt is (N, C, H, W), which represent ...

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 the technical field of image denoising processing, in particular to a rock core CT image denoising method based on deep learning, which comprises the following steps of: 1, preparing a data set; 2, model forward reasoning: transmitting a noise image into the model to obtain the output of a forward reasoning graph; 3, loss calculation: labeling a feature map output by the model with real data; 4, repeating the step 2 and the step 3, and optimizing the image data according to the weight of the loss ratio through multiple iterations and image resolution category judgment; and finally, outputting a noisy point result by using the trained modeler model so as to remove the noisy points. The de-noised image obtained by the method and a real image are quite close to the real image data in terms of low-level pixel values, high-level abstract features or overall concept and style.

Description

technical field [0001] The invention relates to the technical field of image denoising processing, in particular to a deep learning-based method for denoising a CT image of a rock core. Background technique [0002] The research on the petrophysical structure of stratigraphic reservoir cores is of great significance for improving oil recovery. Due to the complex core structure in stratigraphic reservoirs, the detection of early two-dimensional images is far from meeting the needs of current industrial production. The oil and gas parameters of rocks are often calculated by traditional petrophysical experiments, which are expensive and time-consuming. Nowadays, the use of digital core technology has become one of the important means to study the internal structure of rock cores. With the rapid development of numerical simulation technology and computer hardware, digital core technology has become one of the best methods for petrophysical research. Due to the heterogeneity of ...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/084G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/10012G06N3/048G06N3/045G06T5/70
Inventor 赵军赖强陈伟峰何绪全巫振观焦世祥贾将
Owner SOUTHWEST PETROLEUM 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

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