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

An efficient super-resolution method based on a deep back projection network

A super-resolution and back-projection technology, which is applied in image data processing, instrumentation, computing, etc., can solve problems such as deep network layers, large amount of parameters, and slow operation speed

Active Publication Date: 2019-05-10
TIANJIN UNIV
View PDF4 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing deep super-resolution network has problems such as deep network layers, large amount of parameters, and slow running speed.

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
  • An efficient super-resolution method based on a deep back projection network
  • An efficient super-resolution method based on a deep back projection network
  • An efficient super-resolution method based on a deep back projection network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0062] The principle that the inventive method is based on is as follows:

[0063] Aiming at the problems of the existing deep super-resolution network with deep layers, large amount of parameters, and slow running speed, the present invention develops an efficient super-resolution network based on the DBPN network. Firstly, the error back-projection module is redesigned, The combination of group convolution and 1×1 convolution is used instead of traditional convolution. Group convolution can effectively reduce the number of parameters of the model and improve the efficiency of the model.

[0064] The parameter amount of the standard convolution is:

[0065] K·K·C in ·C out

[00...

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 efficient super-resolution method based on a deep back projection network. The method comprises the following steps: (1) obtaining a total training set and a test set; (2) preprocessing the total training set to complete data enhancement; (3) scaling the images in the total training set at different scales; and (4) image super-resolution reconstruction is realized basedon the convolutional neural network, and the convolutional neural network totally comprises 27 convolutional layers and specifically comprises three parts of feature extraction, error back projectionand image reconstruction. The combination of the group convolution and the 1 * 1 convolution is used for replacing the traditional convolution to redesign the iteration submodule, and the strategy caneffectively reduce the model parameter quantity and improve the model efficiency; Each iteration sub-module comprises an error feedback mechanism, so that error correction can be carried out in time;in addition, a channel weighting module is introduced, so that the model efficiency can be further improved.

Description

technical field [0001] The invention belongs to the field of computer image processing, in particular to an efficient super-resolution method based on a deep back-projection network. Background technique [0002] The amount of information contained in an image depends to a large extent on the resolution of the image. Increasing the resolution of the image can improve the visual effect of the image and make it more in line with the processing requirements of humans and computers. It is used in video surveillance, medical imaging, It has a wide range of applications in fields such as biometric information identification. [0003] Existing Single Image Super Resolution (SISR) methods can be divided into interpolation methods, reconstruction-based methods and learning-based methods. Interpolation-based methods mainly include the nearest neighbor algorithm, bicubic interpolation, etc.; this type of method is simple and easy to process in real time, but the reconstructed image ha...

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): G06T3/40
Inventor 杨爱萍杨炳旺王金斌鲁立宇何宇清
Owner TIANJIN 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