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

JPEG compressed image super-resolution reconstruction method based on convolutional neural network

A convolutional neural network and super-resolution reconstruction technology, applied in the field of image processing, can solve problems such as difficulty in obtaining reconstruction effects

Inactive Publication Date: 2018-01-09
SICHUAN UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to obtain satisfactory reconstruction results by directly using traditional super-resolution methods to reconstruct compressed images in real life.

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
  • JPEG compressed image super-resolution reconstruction method based on convolutional neural network
  • JPEG compressed image super-resolution reconstruction method based on convolutional neural network
  • JPEG compressed image super-resolution reconstruction method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The present invention will be further described below in conjunction with accompanying drawing:

[0013] figure 1 Among them, the JPEG compressed image super-resolution reconstruction method based on convolutional neural network can be divided into the following three steps:

[0014] (1) Construct a super-resolution reconstruction model based on a convolutional neural network for JPEG compressed images;

[0015] (2) Utilize the training image, the convolutional neural network constructed in the training step (1);

[0016] (3) Use the convolutional neural network model trained in step (2) to reconstruct the low-resolution image compressed by JPEG.

[0017] Specifically, in the step (1), we construct as figure 1 The reconstruction model based on convolutional neural network is shown. Specifically, the constructed model consists of a decompression effect network, a resolution enhancement network and a quality enhancement network. Among them, the decompression effect n...

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 JPEG compressed image super-resolution reconstruction method based on a convolutional neural network (CNN). The method mainly includes the following steps of: constructing asuper-resolution reconstruction model based on the CNN for a JPEG compressed image; training the constructed CNN by using a training image; reconstructing a JPEG-compressed low-resolution image by using a trained CNN model. The constructed CNN framework comprises a decompression effect network, a resolution enhancement network and a quality enhancement network, and can be subjected to end-to-end optimization training. The method of the present invention can reduce the compression noise in the JPEG compressed image and improve the resolution of the JPEG compressed image, can be applied to the fields of image and video compression, digital multimedia communication and the like.

Description

technical field [0001] The invention relates to a quality improvement technology of a JPEG compressed image, in particular to a super-resolution reconstruction method of a JPEG compressed image based on a convolutional neural network, and belongs to the field of image processing. Background technique [0002] In military and medical fields, high-quality images and videos help to obtain richer and more accurate information, among which the resolution of images and videos is an important indicator. With the improvement of people's living standards and the popularization of high-definition display devices, people have higher and higher requirements for the resolution of images and videos in daily life. In recent years, imaging equipment used in various fields has also developed greatly, and images and videos with higher resolution and better quality can be obtained. However, in some cases, due to the constraints of various factors such as economy and environment, the obtained ...

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
Inventor 何小海陈洪刚任超卿粼波滕奇志吴小强陶青川
Owner SICHUAN 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