A method and device for super-resolution image texture optimization

A super-resolution image and texture optimization technology, applied in the field of image super-resolution, can solve problems such as unsatisfactory texture optimization effect

Inactive Publication Date: 2020-12-08
BEIJING UNIV OF POSTS & TELECOMM
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such methods only use limited texture instances or internal information as prior information to perform image texture reconstruction, and do not properly classify texture blocks, so the optimization effect on texture is not ideal

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
  • A method and device for super-resolution image texture optimization
  • A method and device for super-resolution image texture optimization
  • A method and device for super-resolution image texture optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0100] The concrete implementation of the present invention is described in detail below, it is necessary to point out here that the following implementation is only used for further description of the present invention, and can not be interpreted as limiting the protection scope of the present invention. Some non-essential improvements and adjustments still belong to the protection scope of the present invention.

[0101] The invention provides a method and device for super-resolution image texture optimization based on time domain and fractional frequency domain feature screening and mapping kernel learning.

[0102] An embodiment of the present invention provides a method for optimizing texture of a super-resolution image based on mapping kernel learning. see figure 1 , figure 1 A flowchart of a method for super-resolution image texture optimization according to an embodiment of the present invention, including the following steps:

[0103] Step 101, inputting a training...

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

A method and device for super-resolution image texture optimization, implemented based on time-frequency feature extraction and mapping kernel learning, the method includes: 1) training local texture maps based on local texture blocks of time-domain and fractional-order frequency-domain features Block sample filter, which screens samples with obvious texture features from external samples as training samples for the mapping kernel training module; 2) learns texture blocks to optimize the mapping kernel based on local texture blocks learned from external samples; 3) to be optimized The image is optimized for texture. The method and device of the invention can make the texture of the super-resolution image clearer and more natural.

Description

technical field [0001] The invention relates to the technical field of image super-resolution, in particular to a method and device for super-resolution image texture optimization based on time domain and fractional frequency domain feature screening and mapping kernel learning. Background technique [0002] As an important information carrier, images play an important role in both daily life applications and scientific research applications. In an image, higher resolution means that the image will contain richer information and more detailed details. However, due to the interference and compression of the image during the imaging process or network transmission, the pictures we get are often blurred A low-resolution image of a small size. Image super-resolution technology hopes to reconstruct a clear large-scale high-resolution image from the degraded low-resolution image, realize the reverse process of the image degradation process, and restore richer image information. ...

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 Patents(China)
IPC IPC(8): G06T3/40G06T5/00G06T7/40G06K9/62
CPCG06T3/4053G06T5/005G06T7/40G06T2207/20081G06F18/2411
Inventor 段沛奇康学净张雪松吕远郑林誉
Owner BEIJING UNIV OF POSTS & TELECOMM
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