Still image compression method based on deep convolutional neural network

A neural network and deep convolution technology, which is applied in the fields of still image compression, image compression and image super-resolution reconstruction based on deep convolutional neural network, which can solve the aliasing effect and ringing effect of decoded images, affecting subjective visual effects, etc. question

Active Publication Date: 2017-08-04
SICHUAN UNIV
View PDF2 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the case of medium and low bit rates, JPEG2000 standard decoding images have serious jagged and ringing effects, which seriously affect people's subjective visual effects.

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
  • Still image compression method based on deep convolutional neural network
  • Still image compression method based on deep convolutional neural network
  • Still image compression method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with accompanying drawing:

[0022] figure 1 In, a still image compression method based on a deep convolutional neural network, including the following steps:

[0023] (1) Down-sampling the original image to be compressed at the encoding end to obtain a low-resolution image, then JPEG2000 standard encoding is performed on the low-resolution image to obtain an encoded low-resolution image, and then JPEG2000 standard decoding is performed to obtain a decoded low-resolution image image;

[0024] (2) At the encoding end, a deep convolutional neural network is used to suppress the compression effect on the decoded low-resolution image, and obtain a low-resolution image that suppresses the compression effect;

[0025] (3) At the encoding end, the super-resolution method based on the deep convolutional neural network is used to reconstruct the low-resolution image suppressing the compression effect twice to...

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 still image compression method based on a deep convolutional neural network. The still image compression method mainly comprises the following steps of: carrying out downsampling on an original image at an encoding end and carrying out encoding and decoding by utilizing a JPEG2000 standard; carrying out an inhibition compression effect on a decoded image by utilizing the deep convolutional neural network; reconstructing an inhibition compression effect image by adopting a super-resolution method; carrying out subtraction on the original image and a decoded high-resolution image to obtain a residue image and carrying out targeted encoding; forming bit stream by an encoded low-resolution image, the residual image and auxiliary information and transmitting the bit stream; carrying out decoding by a decoding end to obtain a decoded low-resolution image, residual image and auxiliary information; and processing the decoded low-resolution image to obtain a decoded high-resolution image, carrying out superposition on the decoded high-resolution image and the decoded residual image to obtain a finally decoded high-resolution image. The still image compression method disclosed by the invention has higher rate distortion performance than the JPEG2000 standard.

Description

technical field [0001] The invention relates to image compression and image super-resolution reconstruction technology, in particular to a still image compression method based on a deep convolutional neural network, which belongs to the field of image communication. Background technique [0002] The purpose of image compression is to store and compress more efficiently. As one of the basic technologies in the image field, image compression has always been concerned by researchers. With the popularization of high-resolution images and videos, image compression technology becomes more important. The JPEG2000 standard is an image compression technology based on discrete wavelet transform, which has better compression performance than the JPEG standard. However, in the case of medium and low bit rates, JPEG2000 standard decoding images have serious jagged and ringing effects, which seriously affect people's subjective visual effects. [0003] Image super-resolution reconstruc...

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): H04N19/59H04N19/61H04N19/154G06T3/40
CPCG06T3/4046G06T3/4053H04N19/154H04N19/59H04N19/61
Inventor 何小海陈敬勖陈洪刚卿粼波滕奇志吴小强王正勇
Owner SICHUAN 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