Image super-resolution method based on densely linked neural network, storage medium and terminal

A neural network and super-resolution technology, applied in the field of medical image and satellite image processing, can solve problems such as complex network speed, achieve good image super-resolution effect, avoid repeated extraction, and improve the effect.

Inactive Publication Date: 2019-03-29
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the deficiencies of the prior art, provide an image super-resolution method, s

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
  • Image super-resolution method based on densely linked neural network, storage medium and terminal
  • Image super-resolution method based on densely linked neural network, storage medium and terminal
  • Image super-resolution method based on densely linked neural network, storage medium and terminal

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0048] Example 1

[0049] The image super-resolution method based on the densely linked neural network provided in this embodiment has important application value in the fields of surveillance equipment, satellite images, and medical images. This method is used to reconstruct the corresponding high-resolution image from the observed low-resolution image. It is a reconstruction method based on a single low-resolution image and solves the problem of complicated and slow speed in the prior art network.

[0050] Such as figure 1 As shown, the method includes the following steps:

[0051] A: Image preprocessing. In this embodiment, a picture data set is required as the training set of the network. Through this step, the size of the read input image is 28x28, and the generated high-resolution image corresponding to twice the size is 56x56. Specifically, this step mainly includes:

[0052] A1: Randomly cut the training image to get the corresponding high-resolution image Label.

[0053] Bec...

Example Embodiment

[0114] Example 2

[0115] Based on the implementation of embodiment 1, this embodiment also provides a storage medium on which computer instructions are stored, and when the computer instructions are executed, the image super-resolution method based on densely linked neural network described in embodiment 1 is executed. step.

[0116] Based on this understanding, the technical solution of this embodiment essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random acces...

Example Embodiment

[0117] Example 3

[0118] Based on the implementation of embodiment 1, this embodiment also provides a terminal, including a memory and a processor, the memory stores computer instructions that can run on the processor, and when the processor runs the computer instructions Perform the steps of the image super-resolution method based on dense link neural network described in embodiment 1.

[0119] The functional units in the embodiments provided by the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

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 an image super-resolution method based on a densely linked neural network, a storage medium and a terminal. The method includes: preprocessing an image; performing Feature extraction: Building a dense-linked neural network, inputting the low-resolution image Input from the entrance of the dense-linked neural network, and extracting the feature information contained in the Input after calculation; Predicting the super-resolution image and updating the network parameters: performing upsampling/deconvolution on the feature-extracted image to obtain the predicted image predict; calculating the error values between the predicted image predict and the real image label, and updating the parameters of the densely linked neural network in the reverse direction; and performing super resolution reconstruction. The method can remarkably improve the ability of extracting the low-frequency and high-frequency features of an image by a depth neural network, improve the effect of the image super-resolution, and improve the ability of providing information by a picture, so that the invention is applied in the field of expecting to obtain a high-resolution image and providingmore details by the picture.

Description

technical field [0001] The invention relates to the field of medical image and satellite image processing, in particular to an image super-resolution method, storage medium and terminal based on a dense link neural network. Background technique [0002] Super-resolution technology SR (Super-Resolution) refers to reconstructing corresponding high-resolution images from observed low-resolution images, which has important application value in the fields of monitoring equipment, satellite images, and medical imaging. SR can be divided into two categories: reconstructing high-resolution images from multiple low-resolution images and reconstructing high-resolution images from a single low-resolution image. SR based on deep learning is mainly based on a single low-resolution reconstruction method, namely Single Image Super-Resolution (SISR). [0003] SISR is an inverse problem. For a low-resolution image, there may be many different high-resolution images corresponding to it. Ther...

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): G06T3/40G06N3/04G06N3/08
CPCG06N3/084G06T3/4053G06N3/048G06N3/045
Inventor 匡平马霆松王豪爽郭雯霞陈鹏彭亮
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap