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

A hardi compressed sensing super-resolution reconstruction method based on deep dictionary learning

A technology of super-resolution reconstruction and dictionary learning, applied in instruments, graphics and image conversion, computing, etc., can solve the problem of weak dictionary expression ability, and achieve good nerve fiber reconstruction ability, small amount of sampling data, and fast data sampling speed. Effect

Active Publication Date: 2020-07-17
CHENGDU UNIV OF INFORMATION TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing dictionary learning method for joint compressed sensing is mainly designed for HARDI image denoising, and the learning algorithm is mainly evolved according to the conventional classic dictionary learning algorithm, and the expression ability of the obtained dictionary is relatively weak

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
  • A hardi compressed sensing super-resolution reconstruction method based on deep dictionary learning
  • A hardi compressed sensing super-resolution reconstruction method based on deep dictionary learning
  • A hardi compressed sensing super-resolution reconstruction method based on deep dictionary learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] A detailed description will be given below in conjunction with the accompanying drawings.

[0028] The original signal in the present invention refers to a high-resolution signal that has not been down-sampled.

[0029] The signal to be reconstructed in the present invention refers to a low-resolution signal obtained after the sample is down-sampled by the measurement matrix.

[0030] figure 1 is a schematic diagram of compressed sensing for a single-layer dictionary. Such as figure 1 As shown, x is the original signal. In practice, the acquisition time of the original signal is too long, which is not convenient for acquisition. y is the signal to be reconstructed, that is, the actual measurement signal, α is the sparse signal, Ψ and Φ are the dictionary and the measurement matrix, respectively.

[0031] The mathematical expression of single-layer compressed sensing is:

[0032] x=Ψ*α (1)

[0033] y=Φ*Ψ*α (2)

[0034] The data is compressed and sampled by measuri...

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 a HARDI compressed sensing super-resolution reconstruction method based on deep dictionary learning, which includes preprocessing the collected high-angle diffuse images to obtain training data, and establishing a deep network model including multi-layer dictionaries for dictionary learning. The training data is used to train the constructed deep network model, and the orthogonal triangular decomposition is used to extract the orthogonal vectors in order as the initial dictionary. The data whose density is much lower than the original data is used as the test data, and the sparse representation coefficient is obtained based on the test data, and finally the reconstructed three-dimensional diffusion magnetic resonance image of the human body is generated through the direction distribution function obtained by radial integration. The invention requires less sampling data to reconstruct the diffusion magnetic resonance image with the same resolution. With faster data sampling speed. It has better nerve fiber reconstruction ability.

Description

technical field [0001] The invention relates to the fields of compressed sensing and medical imaging, in particular to a high-angle-resolution diffuse imaging compressed sensing super-resolution reconstruction method based on deep dictionary learning. Background technique [0002] For HARDI imaging, the existing compressed sensing technology mainly performs compressed sensing reconstruction of data on the spatial resolution or angular resolution of the data alone. The brain is sampled and measured by reducing the number of spatial or angular upsampling, and then using these small sampled data to obtain high-resolution images through dictionary reconstruction. Recently, joint compressive sampling methods for both spatial and angular aspects have emerged. At the same time, the number of samples in space and angle is reduced, which further reduces the number of data samples required for image reconstruction. Most of the dictionaries used are a priori dictionaries, which are d...

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 Patents(China)
IPC IPC(8): G06T3/40
Inventor 杨智鹏罗苏阳符颍吴锡
Owner CHENGDU UNIV OF INFORMATION TECH
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