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

Image super-resolution method based on overcomplete dictionary learning and sparse representation

A sparse representation and super-resolution technology, applied in the field of image processing, which can solve the problems of color blocking, overfitting, underfitting, etc.

Inactive Publication Date: 2009-10-14
FUDAN UNIV
View PDF4 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, even for isomorphic datasets, it is a key issue to solve the representation on low-resolution datasets, which is prone to overfitting or underfitting.
Finally, for color images, the usual method is to convert the RGB color space of the image to the YUV color space, and only do super-resolution on the brightness information (Y), and just do ordinary interpolation for the other two chromaticities, In this way, it is easy to produce block effect of color

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 super-resolution method based on overcomplete dictionary learning and sparse representation
  • Image super-resolution method based on overcomplete dictionary learning and sparse representation
  • Image super-resolution method based on overcomplete dictionary learning and sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0044] Such as figure 1 , 2 As shown, the present invention is an image super-resolution method based on dictionary learning and sparse representation. First, the training image is used to obtain high-resolution and low-resolution dictionary pairs with isomorphic properties, and then the low-resolution dictionary is used for the test image Perform sparse representation, and finally use a high-resolution dictionary for super-resolution reconstruction of the image. At the same time, the present invention also uses a bilateral filter to perform super-resolution reconstruction of chroma UV.

[0045] The specific steps of dictionary learning are as follows:

[0046] 1. Initialize settings. The size of the low-resolution image block is set to 3×3, the overlapping part is 1 pixel, and the super-resolution multiple is 4; therefore, the size of the high-re...

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 method based on overcomplete dictionary learning and sparse representation. The method comprises the following steps of: extracting two overcomplete dictionaries (a low-resolution image block dictionary and a high-resolution image block dictionary) in a large-scale dataset and utilizing the two overcomplete dictionaries to realize super-resolution reconstruction of image sparse representation. Simultaneously, in order to further improve the super-resolution effect of color images, the invention also proposes UV chromaticity super-resolution reconstruction based on super-resolution luminance information. The image super-resolution method has wide application prospect in the fields of video monitoring, medical imaging, remote sensing image and the like.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a super-resolution algorithm based on dictionary learning and sparse representation. Background technique [0002] Super-resolution research is expected to enlarge low-resolution images into high-resolution images, and keep the details in the image without distortion and mosaic effects. Due to its huge potential applications in video surveillance, medical imaging, remote sensing images and other fields, it has been paid more and more attention. Although super-resolution technology has been proposed for some time, a unified framework has not been formed so far. The main difficulty is that since the same low-resolution image can be degenerated by multiple high-resolution images, mathematically speaking, what super-resolution research expects to solve is essentially a one-to-many problem, also known as an ill-conditioned problem. Therefore, to narrow the scope of its so...

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
Inventor 浦剑张军平
Owner FUDAN UNIV
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