Image coding and decoding method, system, equipment and medium

A decoding method and image encoding technology, applied in the field of image compression, can solve the problem of low compression performance, achieve the best performance, strong scalability, and rich intermediate features

Pending Publication Date: 2022-08-09
XI AN JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the technical problems existing in the prior art, the present invention provides an image encoding and decoding method, system, equipment and medium to solve the problem that the existing encoding framework only uses the partial correlation of images, and for complex images, its compression Technical issues with lower performance

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
  • Image coding and decoding method, system, equipment and medium
  • Image coding and decoding method, system, equipment and medium
  • Image coding and decoding method, system, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0117] This embodiment provides an image encoding and decoding method, which specifically includes the following steps:

[0118]Step 1. Build a preset image preprocessing model; wherein, the preset image preprocessing model is a Gaussian denoiser based on a deep convolutional neural network; the Gaussian denoiser based on a deep neural network includes several level denoising model unit; the level of each level denoising model unit is adapted to the noise level of the image to be processed; the denoising model unit is a denoising network structure related to natural images.

[0119] as attached figure 1 As shown, in this embodiment 1, the denoising model unit at each stage includes a first convolution layer, a first multi-correlation branch module, a first discrete wavelet forward transform module, a first 1× 1 convolutional layer, second multi-correlation branch module, second discrete wavelet forward transform, second 1×1 convolutional layer, third multi-correlation branch ...

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 image coding and decoding method, system, equipment and medium, and the method comprises the steps: carrying out the preprocessing of an original image, carrying out the compressed sensing measurement, dividing a measurement value into different parts, progressively employing a part of the measurement value to carry out the iteration, and carrying out the reconstruction of the original image through gradient stepping and Gaussian denoising, thereby obtaining a prediction image, carrying out compressed sensing measurement on the predicted image so as to obtain predicted measurement values of other parts, and carrying out quantization and entropy coding on residual errors of the original measurement values and the predicted measurement values; a Gaussian de-noising device based on a deep convolutional neural network is utilized to carry out de-noising processing on an original image, so that the correlation between pixels of a noisy image can be captured efficiently; meanwhile, the image coding problem is converted into the image Gaussian denoising problem under the given code rate constraint, adaptation to different application scenes is achieved by replacing a Gaussian denoising device used in the image Gaussian denoising problem, and high expandability is achieved.

Description

technical field [0001] The invention belongs to the technical field of image compression, and particularly relates to an image encoding and decoding method, system, device and medium. Background technique [0002] Images and videos can reproduce real scenes or express things in an intuitive form; as the volume of image data and video data becomes larger and larger, it brings huge pressure on the storage space and transmission bandwidth of images or videos At the same time, higher requirements are also put forward for the existing image and video coding standards; for the coding process of images or videos, a certain prediction reference value is generally selected for quantization and entropy coding to obtain code streams; and the upper limit of encoder performance is determined The key lies in the choice of the prediction reference value and the way to restore and reconstruct the original data. [0003] At present, the traditional coding methods based on transform domain c...

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): G06T9/00G06T5/00G06N3/08G06N3/04
CPCG06T9/002G06T5/002G06N3/08G06T2207/20081G06N3/045
Inventor 侯兴松王榆森
Owner XI AN JIAOTONG 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