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

Baseline-based image super-resolution reconstruction method and system

A super-resolution reconstruction and high-resolution image technology, applied in the field of computer vision, can solve the problems of no original image, blurred image, etc.

Active Publication Date: 2020-07-07
SHANDONG NORMAL UNIV
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the inventors found that the image super-resolution reconstruction method based on the conditional generative confrontation network will have the problem of image blurring at a higher magnification, and at the same time, there will be details that the original image does not have.

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
  • Baseline-based image super-resolution reconstruction method and system
  • Baseline-based image super-resolution reconstruction method and system
  • Baseline-based image super-resolution reconstruction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] In one or more embodiments, a baseline-based image super-resolution reconstruction method is disclosed, referring to Fig. 1(a)-(b), wherein Fig. 1(b) is a generator model; including the following steps:

[0042] Step 1: Select the training set;

[0043] A data set composed of 91 images was selected as a training sample, and the data set was divided into 24,800 sub-images, each of which was 33X33 in size, and trained multiple times to prove the baseline-based super-resolution reconstruction model proposed by the embodiment of the present invention availability.

[0044] Step 2: Build a baseline-based super-resolution reconstruction model. refer to Figure 2-Figure 3 ,in, figure 2 For the SRCNN model, image 3 as the baseline block diagram model.

[0045] Baseline-based convolutional neural network models input low-resolution images and output high-resolution images.

[0046] Two continuous residual network models built with the SRCNN network as the baseline. Each ...

Embodiment 2

[0072] In one or more embodiments, a baseline-based image super-resolution reconstruction system is disclosed, comprising:

[0073] means for building baseline-based convolutional neural network models;

[0074] A device for constructing an image super-resolution reconstruction model based on a conditional generative confrontation network;

[0075] It is used to input the low-resolution image to be reconstructed into the baseline-based convolutional neural network model, and the output of the neural network model is used as the input of the image super-resolution reconstruction model based on the conditional generation confrontation network, and finally obtain the super-resolution reconstruction image device.

[0076] The specific implementation method of the above device is the same as the method disclosed in the first embodiment, and will not be repeated here.

Embodiment 3

[0078] In one or more embodiments, a terminal device is disclosed, including a server, the server includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor executes the The program implements the baseline-based image super-resolution reconstruction method in Embodiment 1. For the sake of brevity, details are not repeated here.

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 baseline-based image super-resolution reconstruction method and a baseline-based image super-resolution reconstruction system. The baseline-based image super-resolution reconstruction method comprises the steps of: constructing a baseline-based convolutional neural network model; constructing an image super-resolution reconstruction model based on a conditional generativeadversarial network; and inputting a to-be-reconstructed low-resolution image into the baseline-based convolutional neural network model, taking the output of the neural network model as the input ofthe image super-resolution reconstruction model based on the conditional generative adversarial network, and finally acquiring a super-resolution reconstruction image. According to the baseline-basedconvolutional neural network model, two residual learning networks are stacked and used for learning high-frequency residual components which cannot be recovered by adopting a traditional image super-resolution method, and the quality of the obtained high-resolution image is improved by learning more residual information and constructing a CNN-based image super-resolution model.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a baseline-based image super-resolution reconstruction method and system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Image super-resolution reconstruction is an important branch of computer vision. It can obtain high-resolution images through the process of feature extraction, mapping, and reconstruction of low-resolution images through convolutional neural network models. Single image super-resolution is an important aspect of computer vision. The branch aims to generate a corresponding high-resolution image from a low-resolution image through a convolutional neural network. It has a wide range of applications in pedestrian detection, vehicle detection, face recognition and other scenarios. At present, the key problem to ...

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): G06T3/40G06N3/08G06N3/04
CPCG06T3/4053G06T3/4046G06N3/082G06N3/045
Inventor 乔建苹李慧娜
Owner SHANDONG NORMAL 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