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

Method for realizing high-density compression and decompression of picture based on machine learning

A machine learning, high-density technology, applied in instruments, image coding, image data processing, etc., can solve problems such as excessive image storage, and achieve the effect of large compression ratio

Active Publication Date: 2019-06-28
杭州环形智能科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of excessive storage of pictures in the existing technology, the present invention provides a feature based on machine learning that can retain pictures. A method that can obtain a large compression ratio and realize high-density compression and decompression of images

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
  • Method for realizing high-density compression and decompression of picture based on machine learning
  • Method for realizing high-density compression and decompression of picture based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] see figure 1 , a method for realizing high-density image compression and decompression based on machine learning, the steps are as follows,

[0033] a) Construct an intelligent learning model model, the model model identifies each key element in the image, such as features 1, 2, and 3, and then screens out relevant features.

[0034]b) Fill the image, leaving the background image Image(b), then store the identified features and key elements, store the compressed background layer, and finally obtain the compressed image.

[0035] c), decompress, retrieve key elements, such as background information and feature information, match element prototypes from the element library, and then restore the elements to the position of the image according to the position of the elements, and restore multiple elements in turn.

[0036] d) According to the characteristics of each element, the elements retrieved from the element library are finely deformed and restored;

[0037] e) Extr...

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 method for realizing high-density compression of pictures based on machine learning. The decompression method comprises the following steps of: constructing an intelligent learning model to identify key elements in an image, screening out relevant characteristics, further filling the image, remaining a background image Image (b), storing the identified characteristics andthe key elements, and storing the compressed background image layer to obtain a compressed image. A key element is called during decompression; matching element prototypes from an element library; restoring the element to the position of the image according to the position of the element. The method comprises the following steps: sequentially restoring a plurality of elements, carrying out fine deformation and position restoration on the elements retrieved in an element library according to the characteristics of each element, further extracting a background in a background library to reappear, using Gaussian blur, blurring and superposing gaps at the edges, smoothing the joints and the edges of different image layers, generating a final image with similar characteristics, and realizing decompression. Compression ratio is ultra-large, and the requirement of existing picture storage can be met.

Description

technical field [0001] The invention relates to a method for realizing high-density compression and decompression of pictures based on machine learning. Background technique [0002] In modern society, due to the era of big data, the existing pictures have higher and higher pixels, and their storage capacity has also increased, resulting in an excessively large overall picture data storage capacity, causing many changes to picture preservation and transfer. For ease of transfer, images are usually compressed, and existing lossless compression capabilities are limited. The lossy compression compression ratio is only two orders of magnitude. In reality, there are many pictures that do not need to preserve the details of the pictures, but the details cannot be avoided during the compression process. Relatively speaking, the compression ratio is not very ideal. [0003] For example, a raw image file with a size of 1M is about 200k when compressed into png format, and about 60k...

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): G06T9/00
Inventor 周元海
Owner 杭州环形智能科技有限公司
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