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

An image compression method and system based on a generative countermeasure network

An image compression and generative technology, applied in the direction of image communication, digital video signal modification, electrical components, etc., can solve the problems of complex process, slow data compression and restoration speed, etc., and achieve the effect of fast compression and reconstruction speed and high similarity.

Inactive Publication Date: 2018-12-18
北京飞搜科技有限公司
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides an image compression method and system based on a generative confrontation network in order to solve the defects of the traditional image compression algorithm with complex process and relatively slow data compression and restoration 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 image compression method and system based on a generative countermeasure network
  • An image compression method and system based on a generative countermeasure network
  • An image compression method and system based on a generative countermeasure network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the Invent a modular embodiment, not an entire embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0041] Generative adversarial networks are a method of unsupervised learning that learn by letting two neural networks play games with each other. Mutual game learning of Generative Model and Discriminative Model produces quite good output. The embodiment of the present invention uses a generative adversarial learning method to train a generative network and ...

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 embodiment of the invention provides an image compression method and a system based on a generated countermeasure network. Tranining data is obtained. The training data includes an original imageand a corresponding compressed image. According to the training data, the generated network and discrimination network are trained. The image generation network model is obtain. The image to be compressed is inputted into the image generation network model for compression and reconstruction. Compared with the traditional image compression algorithm, the invention utilizes the generation type confrontation learning method to train the generation network and the discrimination network, optimizes the parameters of the generation network, and obtains the image generation network model. The image can be compressed quickly by using the image generation network model. Compared with the compression algorithm based on coding redundancy, the compression and reconstruction speed is faster. Compared with the compression algorithm based on spatial redundancy, the similarity between the compressed image and the original image is higher.

Description

technical field [0001] The present invention relates to the technical field of image compression, and more specifically, to an image compression method and system based on a generative confrontation network. Background technique [0002] In daily life, no matter what kind of transmission medium is used to transmit information, it will encounter the problem of transmitting and storing a large amount of image data. For the transmission of a large amount of image data, it is necessary to ensure the quality and speed of its transmission, and its storage must also consider its size and capacity. Therefore, in order to solve the transmission and storage of a large amount of image data, in the current transmission medium, there is a limitation of transmission bandwidth, so how to transmit as many moving images as possible under certain restrictions, how to compress the image data to the maximum extent, and Ensuring that the reconstructed image after compression can be accepted by ...

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): H04N19/70
CPCH04N19/70
Inventor 许靳昌董远白洪亮熊风烨
Owner 北京飞搜科技有限公司
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