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

Super-resolution image reconstruction method based on non-local dictionary learning and biregular terms

A super-resolution reconstruction and non-local dictionary technology, applied in the field of image processing, can solve problems such as image artifacts, ignoring prior knowledge of ultra-low resolution images, distortion, etc., to improve accuracy, maintain edge and texture details , the effect of improving quality

Active Publication Date: 2013-09-11
XIDIAN UNIV
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although most reconstruction methods based on dictionary learning can effectively use the prior information of external high-resolution sample images, this type of method ignores the prior knowledge of the ultra-low resolution image itself, resulting in artifacts and distortions in the reconstructed image.

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
  • Super-resolution image reconstruction method based on non-local dictionary learning and biregular terms
  • Super-resolution image reconstruction method based on non-local dictionary learning and biregular terms
  • Super-resolution image reconstruction method based on non-local dictionary learning and biregular terms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Refer to attached figure 1 , concrete steps of the present invention include:

[0024] Step 1. To the initial high-resolution image Carry out adaptive clustering dictionary training to get R cluster centers C center ={C i ,i=1,2,...,R}, the initial expected dictionary set D 0 and the initial set of residual dictionaries d 0 .

[0025] 1a) Extract the initial high-resolution image The high-frequency features of , get the high-frequency feature map G;

[0026] 1b) respectively in the initial high-resolution image Take a 7×7 block on the high-frequency feature image G, and the initial high-resolution image All the image blocks obtained above are arranged sequentially in the form of column vectors to form a set of image blocks Arrange all the feature blocks acquired on the high-frequency feature image G in the form of column vectors to form a set of feature blocks

[0027] 1c) Use K-means clustering method to set feature blocks Perform clustering to get R...

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 super-resolution image reconstruction method based on non-local dictionary learning and biregular terms, and mainly aims to solve the problem that reconstructed images are unnatural due to the fact that prior information of ultralow-resolution images cannot be fully utilized in existing dictionary learning methods. The method includes the main steps: (1), obtaining an initial high-resolution image; (2) training an initial residual dictionary set d0 and an initial expected dictionary set D0; (3) computing an initial non-local regular weight matrix W0 and an initial local kernel regression regular weight matrix K0 on the initial high-resolution image; (4) performing regular optimization processing on an inputted initial high-resolution image to obtain an optimized image; and (5) applying the initial residual dictionary set d0 and the initial expected dictionary set D0 for reconstructing the optimized image to obtain a reconstructed image. The method is capable of reconstructing remote sensing images and effectively maintaining marginal and texture information of the images, and can be used for satellite monitoring and remote-sensing imagery.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image super-resolution reconstruction method, which can be used for super-resolution reconstruction of natural images, medical images and remote sensing images. Background technique [0002] Image super-resolution reconstruction is the inverse problem of reconstructing a high-resolution image from a single or multiple low-resolution images. In general, methods for image super-resolution reconstruction fall into three categories: interpolation-based methods, model-based reconstruction methods, and learning-based methods. Among them, the methods based on interpolation include classic bilinear interpolation method, cubic spline interpolation method and so on. This type of method is simple and fast, but it is easy to cause blurred edges and cannot achieve a good reconstruction effect; methods based on model reconstruction include iterative back projection method, maximum a...

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): G06T5/00G06K9/62
Inventor 缑水平焦李成刘淑珍吴建设杨淑媛马晶晶马文萍
Owner XIDIAN 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