Unlock instant, AI-driven research and patent intelligence for your innovation.

Rapid super-resolution reconstruction algorithm for noisy image

A super-resolution and image technology, applied in the field of image processing, can solve problems such as reducing the stability of the algorithm and making it difficult to determine

Pending Publication Date: 2019-09-10
TIANJIN POLYTECHNIC UNIV
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these algorithms can get good results, the difficult to determine the number of neighbors still reduces the stability of such algorithms

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
  • Rapid super-resolution reconstruction algorithm for noisy image
  • Rapid super-resolution reconstruction algorithm for noisy image
  • Rapid super-resolution reconstruction algorithm for noisy image

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0012] A fast super-resolution reconstruction algorithm for noisy images, such as figure 1 As shown, including high and low resolution dictionary training, selection of similar blocks and weight calculation, and high resolution image block reconstruction,

[0013] C. High and low resolution dictionary training

[0014] When training high- and low-resolution dictionaries, we used 77 standard natural images as the training set, and some of the training images used for high- and low-resolution dictionary training are as follows: figure 2 As shown, the training images used first are noise-free, and the high-resolution images The corresponding low-resolution image It is worth noting here that in order to improve the compatibility between adjacent tiles so that they have the same image size, the latter is first down-sampled and then interpolated to enlarge, as shown in formula (1):

[0015]

[0016] In formula (1), H is the upsampling factor, D is the downsampling factor,...

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 a rapid super-resolution reconstruction algorithm for a noisy image. Most of existing algorithms assume that input images do not contain noise. However, in contrast to the actual situation, most of the images obtained in life contain noise. Firstly, a training method of high-resolution dictionaries and low-resolution dictionaries in a traditional algorithm is used for reference, and on the basis, texture structures of low-resolution image blocks are added into a training process of the dictionaries; in the reconstruction process, column atoms of the sparse dictionary are used as matching objects, and normalization processing is carried out on the input feature vectors and the sparse dictionary, so that the precision is improved. Similar blocks are selected according to the input feature vectors and the similarity of the matching objects, and the weight distribution and reconstruction of the similar blocks are completed through a weight limiting model to obtaincorresponding high-resolution image blocks; and finally, an original estimated high-resolution image and a denoised low-resolution image are reconstructed through weighted average. The two reconstructed images are combined with the iterative back projection to obtain a final image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fast super-resolution reconstruction algorithm for noisy images. Background technique [0002] Single image super-resolution reconstruction is a classic research topic in the field of image processing. In general, its first task is to reconstruct lost high-frequency details from low-resolution images. Traditional interpolation-based super-resolution reconstruction techniques have been widely used and have the advantage of fast implementation. However, in the face of image edges, discontinuous regions, and high-frequency features, ideal results are often not achieved. [0003] In recent years, people have proposed many influential instance-based super-resolution reconstruction methods, and achieved good results, and gradually become the mainstream method in the field of super-resolution reconstruction. The main idea of ​​this method is to learn the mapping relationsh...

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): G06T3/40
CPCG06T3/4053G06T3/4023G06T2207/20081
Inventor 杨亚楠王庆成李楠
Owner TIANJIN POLYTECHNIC UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com