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

A Novel Template-Based Image Super-resolution Enhancement Method

A new type of template and super-resolution technology, which is applied in image enhancement, graphics and image conversion, image data processing, etc., can solve the problem that image super-resolution does not have enough excellent effects, achieve high degree of freedom and adaptability, and improve adaptability , the effect of increasing precision

Inactive Publication Date: 2019-09-17
WUHAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing methods based on reconstruction or enhancement are not good enough for image super-resolution.

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 Novel Template-Based Image Super-resolution Enhancement Method
  • A Novel Template-Based Image Super-resolution Enhancement Method
  • A Novel Template-Based Image Super-resolution Enhancement Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical scheme of the present invention will be further described below in conjunction with the drawings and embodiments.

[0037] The overall flow chart of the present invention is as figure 1 As shown, it specifically includes the following steps (including testing):

[0038] Step 1. Obtain the standard database and some additional image libraries as the original image set, and use it as a data set for testing and verifying the effectiveness of the present invention, including obtaining the images of the standard libraries such as Set5, Set14, B100, and image libraries such as USC-SIPI; Choose any image and do 0.5 times downsampling to obtain a low-resolution image, which is the actual input image.

[0039] Step 2: Perform contour template interpolation on the input image and enlarge it by 2 times to obtain a high-resolution reference image.

[0040] Step 2.1: Pre-set an outline template set through a certain image set, including 57 kinds of outline feature templates. ...

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 relates to an image super-resolution technology based on a new template, which includes: obtaining an original image set, performing 0.5 times downsampling on each image in the image set to obtain a low-resolution image; performing contour template interpolation amplification on the low-resolution image 2 times to obtain a high-resolution reference image; perform new template enhancement on the high-resolution reference image and low-resolution image; calculate the motion matrix between the low-resolution image and the high-resolution reference image through SIFT feature point matching, thereby obtaining the high-resolution reference image The corresponding points of the points on the image in the low-resolution image; by calculating the residual between the points on the high-resolution reference image and the corresponding points in the low-resolution image, the residual image is synthesized, and the residual image and the high-resolution reference image are Overlay to get the final image. The new template can not only effectively enhance the high-frequency information of the image, but also effectively retain the low-frequency information of the image, thus having a wide range of applications in the field of image enhancement.

Description

Technical field [0001] The invention relates to an image super-resolution technology based on a novel template, in particular to an end-to-end single image super-resolution reconstruction method based on the superposition of a novel template and a point spread function. Background technique [0002] The adjustment of the image resolution is a frequently required operation in the application. When faced with various types of images, some classic image processing techniques often fail to achieve better results, especially when there are image texture details or edge stability requirements are high, because the change in resolution is often accompanied by loss of high-frequency information and The amount of information is reduced, so the super-resolution results of the image are often poor and cannot achieve satisfactory goals. Therefore, designing a good image super-resolution method and improving the effect of image super-resolution is a subject worthy of study. [0003] With the ...

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): G06T3/40G06T5/00
CPCG06T3/4053G06T2207/20192G06T2207/20224G06T5/00
Inventor 雷俊锋张赏月肖进胜罗丽邹文涛周永强
Owner WUHAN UNIV
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