Single image super-resolution reconstruction method based on image nonlocal self-similarity

A technology of super-resolution reconstruction and self-similarity, which is applied in the field of super-resolution reconstruction represented by deconvolution sparse coding in a single image, which can solve problems such as ignoring correlation, inaccurate sparse coding coefficients, and high computational complexity

Active Publication Date: 2017-07-14
BEIJING UNIV OF TECH
View PDF5 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One is that a large-scale optimization problem with very high computational complexity needs to be solved in the process of dictionary learning; the other is that in the process of sparse coding and dictionary learning, each image block is considered independently, ignoring the relationship between blocks and blocks. The correlation between the sparse coding coefficients is not accurate enough

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
  • Single image super-resolution reconstruction method based on image nonlocal self-similarity
  • Single image super-resolution reconstruction method based on image nonlocal self-similarity
  • Single image super-resolution reconstruction method based on image nonlocal self-similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The invention provides a method for super-resolution reconstruction of a single image, which is an image feature extraction and image restoration method based on a non-locally similar deconvolution network. The deconvolution network is reconstructed based on the entire image, thereby avoiding the influence of the block effect on the reconstructed image effect; adding the non-local information of the image, in the process of sparsely representing the image structure, it can be explicitly in a unified Under the framework, the inherent local sparsity and non-local self-similarity of natural images can be described at the same time, and the texture details of the image can be better preserved; it includes the following features:

[0037] 1. Image super-resolution reconstruction model based on reconstruction algorithm

[0038] The image resolution enhancement problem refers to given an input low-resolution image, restoring and reconstructing the corresponding high-resolution...

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 single image super-resolution reconstruction method based on image nonlocal self-similarity. The image texture is synthesized through the nonlocal self-similarity of the image and image blank information is filled; and image reconstruction is realized according to the complete theory of a deconvolution neural network. According to the super-resolution reconstruction method based on image nonlocal self-similarity convolution sparse representation, the detail information of the super-resolution image can be better enhanced, the block effect can be reduced and thus the quality of super-resolution image reconstruction can be enhanced.

Description

technical field [0001] The invention belongs to the field of super-resolution of sparse representation, in particular to a method for super-resolution reconstruction of a single image based on non-local self-similarity of the image, mainly applying deconvolution sparse coding to express the super-resolution of a single image reconstruction. Background technique [0002] Image super-resolution reconstruction technology refers to the use of signal processing and computer software to eliminate image quality degradation caused by factors such as imaging system misfocus, motion blur, and non-ideal sampling, and form a clear image with higher spatial resolution. [0003] In the field of computer vision, image super-resolution reconstruction is a very classic problem and is the basis of many computer vision applications, such as face recognition, object tracking, license plate recognition and so on. Depending on the number of input low-resolution images, it can be divided into sin...

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): G06T3/40G06K9/62
CPCG06T3/4076G06F18/22
Inventor 丁文鹏朝丹凤施云惠尹宝才
Owner BEIJING UNIV OF TECH
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
Try Eureka
PatSnap group products