Single-frame image super-resolution reconstruction method on basis of deep learning

A technology of super-resolution reconstruction and deep learning, which is applied in the field of super-resolution reconstruction of single-frame images based on deep learning, and can solve the problems of high cost and limited improvement

Inactive Publication Date: 2015-07-15
HANGZHOU DIANZI UNIV
View PDF4 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Only relying on physical sensing materials and devices to improve image resolution is not only expensive, but also has limited improvement

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
  • Single-frame image super-resolution reconstruction method on basis of deep learning
  • Single-frame image super-resolution reconstruction method on basis of deep learning
  • Single-frame image super-resolution reconstruction method on basis of deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with accompanying drawing.

[0039] Such as Figure 1-3 As shown, the single-frame image super-resolution reconstruction method based on deep learning specifically includes the following steps:

[0040] Step 1. In the process of training the deep network, firstly, two autoencoders are used to obtain the features of low-resolution and corresponding high-resolution image blocks;

[0041] Step 2. In the process of training the deep network, based on the features of the high-resolution and low-resolution image blocks obtained in step 1, train a single-layer neural network to learn the nonlinear mapping relationship between the two features;

[0042] Step 3. In the process of training the deep network, based on the two autoencoders and the single-layer neural network in steps 1 and 2, a three-layer deep network is constructed, with low-resolution image blocks as input and high-resolution image blocks As o...

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 single-frame image super-resolution reconstruction method on the basis of deep learning. The single-frame image super-resolution reconstruction method comprises the following steps: 1, firstly, acquiring characteristics of low-resolution and corresponding high-resolution image blocks by training two automatic encoders; 2, on the basis of the acquired characteristics of the high-resolution and low-resolution image blocks, then training a single-layer neural network and learning a nonlinear mapping relation of two characteristics; 3, on the basis of two automatic encoders and the single-layer neural network, constructing a three-layer deep network, using the low-resolution image block as an input, using the high-resolution image block as an output and finely regulating parameters of the three-layer deep network; 4, according to the obtained three-layer deep network, carrying out single-frame image super-resolution reconstruction, and obtaining the output, i.e. a gray value corresponding to the high-resolution image block, by using a gray value of the low-resolution image block as the input. According to the single-frame image super-resolution reconstruction method on the basis of deep learning, not only is quality of a super-resolution reconstructed image improved, but also super-resolution reconstruction time is shortened and the real-time requirement can be met basically.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a single-frame image super-resolution reconstruction method based on deep learning. Background technique [0002] Super-resolution image reconstruction is the process of reconstructing a high-resolution image or video from a low-resolution image or video. Different from traditional image enhancement, image enhancement is a process in which certain details in the image change from weak to strong, while super-resolution image reconstruction is a reconstruction process in which certain details are created from scratch. At the same time, it also includes Components for image enhancement. [0003] During the imaging process, image quality degradation is inevitable. Only relying on physical sensing materials and devices to improve image resolution is not only expensive, but also limited. Driven by high-resolution image or video application requirements, super-resolution recon...

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): G06T3/40G06T5/50G06N3/02
Inventor 俞俊曾坤
Owner HANGZHOU DIANZI UNIV
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