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

Sparse Representation Single Frame Image Super-resolution Reconstruction Algorithm Based on Principal Structure Separation

A technology of super-resolution reconstruction and sparse representation, which is applied in image analysis, image enhancement, image generation, etc., and can solve problems such as limited effects

Active Publication Date: 2021-05-07
NANJING UNIV OF SCI & TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has very limited effect, so it gradually withdrew from the stage

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
  • Sparse Representation Single Frame Image Super-resolution Reconstruction Algorithm Based on Principal Structure Separation
  • Sparse Representation Single Frame Image Super-resolution Reconstruction Algorithm Based on Principal Structure Separation
  • Sparse Representation Single Frame Image Super-resolution Reconstruction Algorithm Based on Principal Structure Separation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] combine Image 6 , Figure 7 and Figure 8 , for the three pictures "foreman", "comic" and "baby", the super-resolution reconstruction process is performed on the three pictures "foreman", "comic" and "baby" through the sparse representation single-frame image super-resolution reconstruction algorithm based on the separation of the main structure, and the magnification factor is 2 times. Details of peak-to-noise ratio and running time for raw high-resolution images, compared to other novel algorithms.

[0080] Table 1-1 Comparison of signal-to-noise ratio (PSNR) and running time of pictures "foreman", "comic" and "baby" enlarged by 2 times

[0081]

[0082] combine Figure 2-Figure 5 ,from figure 2 and image 3 It can be seen that using the proposed adaptive dictionary size can reconstruct better high-resolution images than other dictionary sizes, and it is well adapted to the characteristics of different images.

[0083] from Figure 4 and Figure 5 It can be...

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 a sparse representation single-frame image super-resolution reconstruction algorithm based on main structure separation. First, the input image is decomposed through the improved correlation full variation to obtain the main structure and texture of the image, and then the main structure and texture of the image are processed separately. For For the main structural component, a self-similar self-driven learning algorithm is constructed for reconstruction, and for the texture component, an external database is used for sparse representation reconstruction. The present invention introduces the correlation total variation for the first time to solve the super-resolution problem, so that the separated main structure has sharp edges, provides strong self-similarity, avoids the complicated calculation of the traditional method while improving the reconstruction effect, and improves the efficiency. The complexity of the texture part is reduced, and various texture patterns can be reconstructed through an external dictionary, which avoids the problem that the dictionary size is not enough to deal with complex pattern changes in the traditional dictionary learning super-resolution method, so that the present invention can deal with different types Image.

Description

technical field [0001] The invention relates to image super-resolution technology, in particular to a sparse representation single-frame image super-resolution reconstruction algorithm based on main structure separation. Background technique [0002] The development of the information technology era has made people have more and more channels for obtaining images. However, due to the limitations of the imaging system, including point spread function (PSF) and spectral aliasing effects, some image quality cannot meet people's expectations. Compared with spending a lot of money On imaging equipment, it saves time and effort to enhance image quality through some software algorithms. Image super-resolution technology is one of them, and it has been widely used in medical images, satellite imaging, target recognition and video surveillance and other fields. [0003] Early super-resolution algorithms were mainly based on multi-frame images, such as optical flow method, POCS, IBP, ...

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): G06T11/00G06T7/40G06T3/40G06K9/46G06K9/62
CPCG06T3/4053G06T11/003G06T2207/20081G06T2211/416G06V10/40G06V10/513G06F18/28
Inventor 隋修宝吴健高航陈钱顾国华刘源吴少迟吴骁斌匡晓东刘程威
Owner NANJING UNIV OF SCI & 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