Image super-resolution reconstruction method of Lorentz fitting fuzzy kernel

A fuzzy kernel and super-resolution technology, applied in the field of visual processing, can solve the problem that the form of point spread function cannot be effectively approximated, affecting the final effect of super-resolution reconstruction, etc., to achieve the effect of improving the effect and wide adaptability

Pending Publication Date: 2021-03-12
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] In order to overcome the deficiencies of the prior art, the present invention provides an image super-resolution reconstruction method of Lorentz fitting blur kernel, aiming at the fact that the existing point spread function form in the image super-resolution process cannot effectively approximate the actual degradation process, that is, with The actual degradation function model has a large approximation error, which directly affects the final effect of super-resolution reconstruction

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
  • Image super-resolution reconstruction method of Lorentz fitting fuzzy kernel
  • Image super-resolution reconstruction method of Lorentz fitting fuzzy kernel
  • Image super-resolution reconstruction method of Lorentz fitting fuzzy kernel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be further described below in conjunction with the accompanying drawings.

[0053] refer to Figure 1 to Figure 6 , an image super-resolution reconstruction method for a Lorentzian fitting blur kernel, comprising the following steps:

[0054] Step 1: Denoising preprocessing, for the low-resolution image sequence g degraded due to the incompatibility of the optical system itself k ∈ R M×N Carry out denoising preprocessing, where k is the number of image sequences, for the degraded image of the actual optical system, the effect of selecting the best notch filter for denoising is better;

[0055] Step 2: Select a frame g from the sequence of low-resolution images 0 As a reference frame, use the diamond search method or optical flow method to search for other low-resolution images g in the sequence l Perform registration to obtain the sub-pixel registration parameter F k , l=1...k-1;

[0056] Step 3: Estimation model of degraded PSF: Accordi...

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 of a Lorentz fitting fuzzy kernel, and aims to solve the problem that the final effect of super-resolution reconstruction is directly influenced because an existing point spread function form in the image super-resolution process cannot be effectively approximate to an actual degradation process, i.e., has a relatively large approximate error with an actual degradation function model. According to the method, a fuzzy effect formed by actual degradation is fully considered, modeling is carried out on the fuzzy effect causedby the actual degradation by adopting linear combination of Lorentz functions, and super-resolution reconstruction is carried out on an image by taking a minimum mean square error as a criterion. According to the method, four parameters are adopted to specifically describe the objective fuzzy process, the objective fuzzy process is closer to the actual fuzzy situation, the model is obtained through theoretical analysis and experimental results, the model is used in a deblurring algorithm, and the image reconstruction effect is improved.

Description

technical field [0001] The invention relates to the field of visual processing, in particular to an image super-resolution reconstruction method of Lorentz fitting blur kernel. Background technique [0002] With the continuous advancement of technology and the wide application of visual processing technology, people's demand for high-quality images has also greatly increased. Image resolution is the key to measure image accuracy and clarity, and there is a direct relationship between image resolution and image clarity. Therefore, how to improve image resolution has become a research hotspot in the field of image processing. A high-resolution image can provide more detailed information. The higher the resolution of the acquired image, the richer the information contained in the image, which is also the basis of various researches on related images. Improving the hardware conditions of imaging equipment is the most direct and effective way to obtain high-resolution images, b...

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): G06T3/40G06T5/00G06T5/50
CPCG06T3/4076G06T5/50G06T5/73
Inventor 黄国兴刘艺鹏卢为党彭宏
Owner ZHEJIANG 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

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