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

Super-resolution image reconstruction method based on structure self-similarity and sparse representation

A super-resolution reconstruction and high-resolution image technology, which is applied in the field of image processing, can solve problems such as large amount of calculation, general image quality, and long time consumption, and achieve the effect of improving quality

Inactive Publication Date: 2013-12-18
XIDIAN UNIV
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods still require a large number of training samples to ensure the effect of reconstruction. For a 256*256 image, it takes at least 10 minutes to complete the entire super-resolution reconstruction process, so the calculation is huge and time-consuming. And the quality of the reconstructed result image is average

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 structure self-similarity and sparse representation
  • Super-resolution image reconstruction method based on structure self-similarity and sparse representation
  • Super-resolution image reconstruction method based on structure self-similarity and sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] The present invention is an image super-resolution reconstruction method based on structural self-similarity and sparse representation. figure 1 , concrete steps of the present invention include:

[0054] Step 1. Input the training sample image pair, and use the training sample image pair to learn to construct a pair of low-resolution dictionaries D with a size of K l and the corresponding high-resolution dictionary D h , to construct a pair of low-resolution dictionaries D of size K l and the corresponding high-resolution dictionary D h The process includes:

[0055] 1a) Input the training image pair, and filter the low-resolution image to extract features. The filter used is f 1 =[-1,0,1], f 3 =[1,0,-2,0,1], The training images used are standard natural images commonly used in the field of image processing. These images can be selected from the library of classical methods, see Figure 2-Figure 5 ,in, figure 2 is the plant training image used in the presen...

Embodiment 2

[0076] The image super-resolution reconstruction method based on structural self-similarity and sparse representation is the same as that in Embodiment 1.

[0077] Wherein, the process of obtaining the weight matrix W in the objective function in step 4.2 includes:

[0078] 4.2a) The jth image block x in the image X to be corrected j In the neighbor area of ​​, find the image block x j The kth nearest neighbor block x k , image block x j The indexes of all the neighbor blocks form the neighbor index set N(j);

[0079] 4.2b) Calculate the image block x according to the following formula j and its neighbor block x k The similarity weight w(j,k) of :

[0080] w ( j , k ) = exp { - | | x j ...

Embodiment 3

[0101] The image super-resolution reconstruction method based on structural self-similarity and sparse representation is the same as in Embodiment 1-2

[0102] 1) Experimental conditions

[0103] The software MATLAB7.9.0 is used as the simulation tool, and the computer configuration is Intel Core2 / 1.8G / 2G.

[0104] 2) Experimental content

[0105] against Figure 6 (a) The displayed low-resolution Lena image is reconstructed by Bicubic interpolation method, Yang (TIP2010) method and the present invention. Obtain the reconstructed image results of the respective methods, and the reconstruction results of the Bicubic interpolation method can be found in Figure 6 (b), the reconstruction results of Yang (TIP2010) method are shown in Figure 6 (c), the super-resolution reconstruction results of the present invention are shown in Figure 6 (d).

[0106] The present invention only reconstructs the grayscale component of the input image, that is, in step 2, the low-resolution L...

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 structure self-similarity and sparse representation. The method includes the main steps of firstly, filtering a set of training sample image to extract features; then, extracting small patches to construct a dictionary including a high-resolution image block and a low-resolution image block in pair, conducting interpolation amplifying on an inputted low-resolution image, conducting filtering to extract the features, solving a reconstructed weight matrix W, conducting iteration to renew a sparse coefficient {alpha i} and a high-resolution image X to be reconstructed; finally, recovering a satisfying high-resolution image till the iteration is convergent. According to the method, the structure self-similarity of the image is used for solving the problem that an existing method is not high in quality. The operation time is short, the efficiency of image reconstruction is high, the quality of the reconstructed image is high, and various natural images which include non-texture images such as animal and plant images and human images and strong-texture images such as architecture images can be reconstructed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image super-resolution reconstruction method, in particular to an image super-resolution reconstruction method based on structural self-similarity and sparse representation, which can be used for super-resolution reconstruction of various natural images Resolution reconstruction. Background technique [0002] Image super-resolution reconstruction aims to break through the resolution limit of the image sensor and reconstruct a higher-resolution image from one or several low-resolution images. In areas such as face recognition in security surveillance videos, object discrimination in remote sensing satellite images, object detection in medical imaging systems, and image and video compression, people are eager to obtain high-resolution images. However, in actual situations, due to the limitations of poor image shooting conditions, serious noise interference, and low resol...

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
IPC IPC(8): G06T5/00
CPCG06T3/4053
Inventor 杨淑媛焦李成汪智易马文萍刘芳侯彪吕远赵玲芳靳红红
Owner XIDIAN 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