Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image processing method, processing apparatus and processing device

An image processing device and image processing technology, applied in the field of image processing, can solve problems such as difficult training, lack of diversity in output images, complex structure, etc., and achieve the effects of easy training, guaranteed diversity, and simple system

Active Publication Date: 2018-02-23
BOE TECH GRP CO LTD
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the structure of the image processing and conversion system in the prior art is complex and difficult to train, and the output images lack diversity

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 processing method, processing apparatus and processing device
  • Image processing method, processing apparatus and processing device
  • Image processing method, processing apparatus and processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Apparently, the described embodiments are only part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] Embodiments of the present invention provide an image processing method, processing device, and processing equipment for realizing image conversion, using a set of generative neural networks for image processing, and the input information of the generative neural networks includes both the image to be converted and the image to be converted. Noise image for generating image detail information. When the generative neural network is used 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

Embodiments of the invention provide an image processing method, processing apparatus and processing device. Image conversion is realized in combination with Laplace transformation and image style features by utilizing a generating neural network, so that an output image after conversion has diversity and is kept consistent with an input image; a system is simple; and training is easy. The image processing method comprises the steps of obtaining a first image comprising N channels, wherein N is a positive integer greater than or equal to 1; and performing image conversion processing on the first image by utilizing the generating neural network to output the output image after conversion, wherein the generating neural network is obtained by training based on a Laplace transformation function.

Description

technical field [0001] The present invention relates to image processing, in particular to an image processing method, processing device and processing equipment. Background technique [0002] Image processing and conversion using deep neural networks is a new technology emerging with the development of deep learning technology. However, the structures of image processing and conversion systems in the prior art are complex and difficult to train, and the output images lack diversity. Therefore, there is a need for an image processing method, device and device for realizing image conversion, which can not only ensure the consistency between the output image and the input image, but also ensure the diversity between different output images. Contents of the invention [0003] The present invention provides an image processing method, processing device and processing equipment, which uses a generative neural network combined with Laplace transform and image style features to ...

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): G06T5/00
CPCG06T2207/20081G06T2207/20084G06T2207/10024G06T2207/10004G06T5/70G06T3/4046G06N3/08G06V10/82G06V10/7753G06N3/047G06N3/045G06T5/10G06T2207/20048G06N3/02G06F18/2155
Inventor 刘瀚文那彦波
Owner BOE TECH GRP CO LTD
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
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