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

Compressed image treatment method and device, electronic equipment and computer readable medium

A technology for compressing images and processing methods, which is applied in the field of image processing, and can solve problems such as limiting the training processing speed of neural networks, long decompression process, and long time spent

Active Publication Date: 2018-01-12
BEIJING KUANGSHI TECH +1
View PDF6 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the decompression process of the JPEG picture is carried out on the CPU (Central Processing Unit, central processing unit) of the computer, and it takes a long time to decompress the JPEG picture into a picture of pure RGB pixels.
For many tasks such as computer vision, the input training sample is a picture in JPEG format. Therefore, using a picture in this format to train a neural network or use a neural network to infer the information in the picture requires a long picture. Decompression process, which limits the processing speed of neural network training and inference

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
  • Compressed image treatment method and device, electronic equipment and computer readable medium
  • Compressed image treatment method and device, electronic equipment and computer readable medium
  • Compressed image treatment method and device, electronic equipment and computer readable medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] figure 1 It is a schematic diagram of an electronic device provided by Embodiment 1 of the present invention.

[0064] refer to figure 1 , an example electronic device 100 for implementing the compressed image processing method and apparatus of the embodiment of the present invention, including one or more processors 102, one or more storage devices 104, an input device 106, an output device 108, and an image acquisition device 110 , these components are interconnected via bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structure of the electronic device 100 shown are only exemplary, not limiting, and the electronic device may also have other components and structures as required.

[0065] The processor 102 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in t...

Embodiment 2

[0072] figure 2 It is a flowchart of a method for training a neural network for compressing pictures provided by Embodiment 2 of the present invention.

[0073] According to an embodiment of the present invention, an embodiment of a method for compressing pictures to train a neural network is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and , although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0074] refer to figure 2 , the method includes the following steps:

[0075] In step S101, an original image is acquired, and the format of the original image is JPEG format, wherein JPEG format is an international image compression standard.

[0076] The original image may be an original image collected by an image collectio...

Embodiment 3

[0105] The embodiment of the present invention also provides a compressed image processing device. The compressed image processing device is mainly used to execute the compressed image processing method provided in the above content of the embodiment of the present invention. The compressed image processing device provided by the embodiment of the present invention will be specifically introduced below.

[0106] Figure 4 It is a schematic diagram of a compressed image processing device provided by Embodiment 3 of the present invention.

[0107] refer to Figure 4 , the device includes an acquisition module 10 , a processing module 20 , a training module 30 and an inference module 40 , wherein the training module 30 includes a construction unit 31 , a first calculation unit 32 and a first update unit 33 .

[0108] Obtaining module 10, is used for obtaining original image, and the format of original image is JPEG format;

[0109] A processing module 20, configured to perform ...

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

An embodiment of the invention provides a compressed image treatment method and device, electronic equipment and a computer readable medium. The compressed image treatment method comprises the following steps: acquiring an original image of which the format is JPEG, and carrying out entropy decoding and inverse quantization treatment on the original image to obtain a pretreated image; carrying outneural network algorithm training on the pretreated image; and finally, deducing the original image by parameters of a neural network of the pretreated image obtained by training to obtain a deducedresult. The method can be carried out on a GPU, and pretreatment time for data decompression required for training and time for deducing of the neural network are shortened.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a compressed image processing method, device, electronic equipment and computer readable medium. Background technique [0002] At present, the decompression process of the JPEG picture is carried out on the CPU (Central Processing Unit, central processing unit) of the computer, and it takes a long time to decompress the JPEG picture into a picture of pure RGB pixels. For many tasks such as computer vision, the input training sample is a picture in JPEG format. Therefore, using a picture in this format to train a neural network or use a neural network to infer the information in the picture requires a long picture. The decompression process limits the training and inference processing speed of the neural network. Contents of the invention [0003] In view of this, the object of the present invention is to provide a compressed image processing method, device, el...

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): G06T9/00G06N3/08
Inventor 周舒畅邹雨恒
Owner BEIJING KUANGSHI TECH
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