An image super-resolution reconstruction method based on joint constraint

A super-resolution reconstruction and high-resolution image technology, applied in the field of image processing, can solve the problems of poor noise suppression ability and poor image reconstruction effect, achieve good reconstruction effect and improve suppression ability

Pending Publication Date: 2019-06-04
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, none of the above methods have a good ability to

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
  • An image super-resolution reconstruction method based on joint constraint
  • An image super-resolution reconstruction method based on joint constraint
  • An image super-resolution reconstruction method based on joint constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0038] Such as figure 1 As shown, an image super-resolution reconstruction method based on joint constraints includes the following steps:

[0039] Step 1: Under the conditions based on low-order constraints, use the K-SVD algorithm for dictionary training and learning, and update the atoms in the dictionary one by one during the dictionary training process;

[0040] (1) Dictionary learning constrained optimization problem:

[0041]

[0042] Among them, D is a dictionary, D opt is the best dictionary after optimization, Λ is the sparse representation coefficient, ε is used to ensure sparsity, Z is the high-resolution image used for dictionary training, t s is the ...

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 an image super-resolution reconstruction method based on joint constraint, and the method comprises the steps: firstly, extracting an image block from a natural image, and under the condition of low-order constraint, carrying out dictionary training learning through a K-SVD algorithm, and updating atoms in the dictionary one by one in the dictionary training process; Secondly, obtaining a graphic block set with the same scale and multi-scale similarity with the image blocks through searching, performing weighted estimation on real codes by utilizing sparse codes of similar image blocks, and introducing difference values between the real codes and the obtained sparse codes as constraint items into an objective function; And finally, for an image block needing to be reconstructed, performing multiplication estimation by utilizing atoms and sparse coefficients in the dictionary to obtain a high-resolution image block. According to the method, the noise influence isweakened by introducing the constraint term, the reconstruction result is enhanced, and more image details are obtained.

Description

technical field [0001] The invention relates to an image super-resolution reconstruction method based on joint constraints, which belongs to the technical field of image processing. Background technique [0002] In recent years, image super-resolution reconstruction has attracted the attention of researchers, and has been widely used in various practical fields, such as medical images, video transmission, etc. However, there are still many problems to be solved in the actual application of image super-resolution reconstruction, such as: the influence of noise, the edge effect of the image, the ringing effect, etc., and the removal of the influence of noise is an urgent problem that needs to be alleviated. [0003] The reconstruction algorithms of super-resolution images mainly include methods based on interpolation, methods based on reconstruction and methods based on learning. Learning-based methods include: neighborhood embedding, sparse representation, and deep learning....

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
CPCY02T10/40
Inventor 杨欣张一帆朱晨周大可李晓川
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap