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

Image blind denoising method for noise modeling based on capsule generative adversarial network

A noise and capsule technology, applied in the field of computer vision, to achieve the effect of enhanced training set data and excellent effect

Inactive Publication Date: 2021-01-08
HEFEI UNIV OF TECH
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the shortcomings of the above-mentioned prior art, the present invention proposes an image blind denoising method based on noise modeling of capsule generation confrontation network, in order to be able to solve problems such as the noise information in the image is not available or the sensor In the case of uncertainty, it is still possible to achieve effective image noise reduction and improve the noise reduction effect

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 blind denoising method for noise modeling based on capsule generative adversarial network
  • Image blind denoising method for noise modeling based on capsule generative adversarial network
  • Image blind denoising method for noise modeling based on capsule generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0079] In order to verify the effectiveness of the method of the present invention, this example adopts mixed noise to verify the noise reduction effect of this method, in this example, the mixed noise that adopts is by 10% uniform noise (distribution interval is [-s, s], 20 % Gaussian noise with a variance of 1 and 70% Gaussian noise with a variance of 0.01, and the peak signal-to-noise ratio (PSNR) is used as the evaluation index, as shown in Table 1.

[0080] Table 1

[0081]

[0082] As can be seen from the experimental results in Table 1, the method of the present invention, in terms of mixed noise denoising, no matter it is the existing method BM3D, WNNM, EPLL under the noise non-blind mode, or the existing method under the noise blind denoising mode Multisclale, DnCNN, and peak signal-to-noise ratio are all higher than these methods, showing the superiority of this method.

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 blind denoising method for noise modeling based on a capsule generative adversarial network, and the method comprises the steps: 1, extracting a smooth noise block from a given noise image; 2, carrying out the noise modeling based on the capsule generative adversarial network; and 3, carrying out the training of a deep CNN, and obtaining a noise reduction model, soas to achieve the blind denoising of an image. According to the method, the defect that the noise reduction effect is poor under the condition that noise information is unknown or a sensor is uncertain in the conventional method can be overcome, so that the noise reduction effect is improved.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to an image blind denoising method based on noise modeling of a capsule generation confrontation network. Background technique [0002] Image denoising is a classic topic in low vision vision and an important preprocessing step in many vision tasks. Following the degradation model y=x+v, the goal of image denoising is to restore a noise-free image x from noisy observations y by reducing noise v. There are basically three types of existing denoising methods: denoising methods based on image priors, blind denoising methods based on noise modeling, and denoising methods based on discriminative learning. [0003] The image priors adopted by image prior-based denoising methods are mainly defined based on human knowledge and may limit the denoising performance; moreover, most methods only utilize the input image when modeling image priority internal information from other images without m...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06N3/048G06N3/045G06T5/70
Inventor 史明光汤亚晨
Owner HEFEI UNIV OF TECH
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