Unlock instant, AI-driven research and patent intelligence for your innovation.

An image filtering method based on dlss deep learning super sampling technology

A super-sampling, deep learning technology, applied in the field of image processing, can solve problems such as shortening processing time

Inactive Publication Date: 2020-11-24
CHONGQING UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, the problem to be solved in the present invention is how to improve the detail processing accuracy and shorten the processing time when using mathematical morphology for image processing

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 filtering method based on dlss deep learning super sampling technology
  • An image filtering method based on dlss deep learning super sampling technology
  • An image filtering method based on dlss deep learning super sampling technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0038] Such as figure 1 As shown, the present invention discloses an image filtering method based on DLSS deep learning super sampling technology, comprising the following steps:

[0039] S1, obtain the original image I L ;

[0040] S2. Use DLSS deep learning super sampling technology to convert the original image I L Generate a profile template;

[0041] S3. Interpolating the contour template to obtain the initial interpolation image I I ;

[0042] For the input original image I L , first use the interpolation algorithm to enlarge it to obtain the initial interpolation image I I . The contour template interpolation algorithm of Getreuer is used to make use of the feature that the contour of the high-resolution image is consistent with the contour of the input low-resolution image, and the shape of the contour of the natural image is estimated in adva...

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 an image filtering method based on DLSS deep learning super sampling technology, which includes the following steps: obtaining the original image I L ; Using DLSS deep learning super sampling technology from the original image I L Generate a contour template; perform a difference on the contour template to obtain the initial interpolation image I I ;Based on original image I L Extract low frequency image I LL and high frequency image I LH ;Convert the original image I L Divided into multiple blocks to be matched; based on the original image I L The multiple blocks to be matched are divided into multiple blocks to generate multiple high-frequency information blocks; the obtained high-frequency information blocks are spliced ​​into an initial interpolation image I I High-frequency information H of size; superimpose high-frequency information H to the initial interpolation image I I Compositing with original image I L Super-resolution images of texture features I H ;For super-resolution image I H Perform filtering to obtain the target image. The present invention combines DLSS deep learning super sampling technology with mathematical morphology, thereby effectively improving the accuracy of detail processing when using mathematical morphology for image processing, and shortening the processing time.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image filtering method based on DLSS deep learning super sampling technology. Background technique [0002] Mathematical Morphology is a nonlinear image processing and analysis tool. In the process of image filtering, a filter composed of morphological opening and closing operators can be used to obtain a good filtering effect. Due to the variety of geometric shapes in the image and the characteristics of noise, it is often necessary to select the appropriate morphological structure element in the morphological filter. Morphology also has a good effect on the processing of satellite cloud images. The structural features of the cloud image are extracted through processing, and the application of the cloud image tends to be objective and quantitative, which reduces human errors and improves the accuracy of forecasting and the degree of automation of weather forecasting. The ap...

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): G06T5/00
CPCG06T2207/20081G06T2207/20084G06T5/70
Inventor 甘平陆鹏张晓松周鑫刘闻通
Owner CHONGQING UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com