Image denoising method, device, equipment and storage medium

An image and image block technology, applied in the field of image processing, can solve the problems of unable to obtain clean pictures, unable to achieve denoising effect, unable to form training data, etc., to reduce the dependence on prior knowledge, efficiently and accurately remove noise, and improve The effect of the noise effect

Active Publication Date: 2018-06-22
SUN YAT SEN UNIV
View PDF6 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If Gaussian noise, which can be artificially generated, is processed under the condition of knowing the noise information, the training data is generally obtained by adding Gaussian noise to the clean image data set, but for the noise in real life, because we do not know the noise information, so the corresponding noise cannot be generated 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
  • Image denoising method, device, equipment and storage medium
  • Image denoising method, device, equipment and storage medium
  • Image denoising method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0079] Embodiment two, see figure 2 , after the acquisition of the first noise image in the noise block set, before constructing the training set according to the noise image and the noise-free image, it also includes:

[0080] S21. Perform noise modeling on the noise block set according to the generative confrontation network, so as to obtain a generator that can generate the same type of noise as the image to be denoised;

[0081] S22. Acquire a second noise image according to the generator;

[0082] Then constructing a training set according to the first noise image and noise-free image includes:

[0083] S23. Construct a training set according to the noise-free image, the first noise image, and the second noise image.

[0084] It should be noted that a training set can also be constructed according to the second noise image and the noise-free image. In order to obtain more training data, it is preferable to use the noise-free image, the first noise image and the The se...

Embodiment 3

[0088] Embodiment three, see image 3 , the acquisition of the smooth block set of the image to be denoised includes:

[0089] S31. Scan the image to be denoised with a preset step size, and intercept global blocks of a preset size to obtain a global block set.

[0090] In this embodiment, the entire picture of the image to be denoised is scanned with a preset step size sg, and a global block of dxd size is intercepted to obtain a global block set P={p1, p2, ..., pn}, where n greater than or equal to 1.

[0091] S32. Scan each global block in the global block set with a preset step size.

[0092] In this embodiment, each global block P1, p2, ..., pn in the global block set P={p1, p2, ..., pn} is scanned with a preset step size sl.

[0093] S33. Intercepting a local block of a preset size for each global block, so as to obtain a local block set corresponding to each global block.

[0094] In this embodiment, after scanning each global block in the global block set, intercep...

Embodiment 4

[0098] Embodiment four, see Figure 4 , performing noise modeling on the noise block set according to the generative confrontation network, so as to obtain a generator that can generate the same type of noise as the image to be denoised, including:

[0099] S41. Select the generative adversarial network model.

[0100] In this embodiment, any kind of generative adversarial network model, such as WGAN, is selected, which is not specifically limited in the present invention.

[0101] S42. Input random noise into the generator of the GAN model.

[0102] S43. Using the noise block set as a real data sample set, train the generative adversarial network model to obtain a generator capable of generating the same type of noise as the image to be denoised.

[0103] In this embodiment, in order to train and obtain a generator that can generate the same type of noise as the image to be denoised, the noise block set is used as the real data sample set of the discriminant model of the ge...

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 denoising method. The method comprises steps: an average block set of a to-be-denoised image is acquired; a corresponding mean value is subtracted from each average block in the average block set to obtain a noise block set; a first noise image in the noise block set is acquired; noise modeling is carried out on the noise block set according to a generative adversarial network to obtain a generator capable of generating the same kind of noise as the to-be-denoised image; a second noise image is acquired according to the generator; according to a noise-free image, the first noise image and the second noise image, a training set is constructed; according to the training set and a discriminative learning method, an image denoising network model is trained; andthe to-be-denoised image is inputted to the image denoising network model to acquire an image after denoising. The invention also provides an image denoising device, equipment and a storage medium. the denoising effects on unknown real noise in real life can be enhanced and the denoising efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image denoising method, device, equipment and storage medium. Background technique [0002] Image is the most commonly used information carrier in today's society, but it is often disturbed and affected by various noises in the process of image acquisition, transmission or storage, which will degrade the image. Image denoising is a very important research direction in the field of image processing, and its purpose is to restore clean images from noisy images. Under different conditions, there are two scenarios for the use of denoising: one is to denoise on the premise of known noise information, which is called specific denoising. The denoising method is used for denoising, such as using median filter to remove salt and pepper noise. The other is to denoise without knowing the noise information, and this kind of removal of unknown noise is called blind denoi...

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): G06T5/00
CPCG06T5/002G06T2207/10004G06T2207/20081
Inventor 陈家炜陈静雯朝红阳杨铭
Owner SUN YAT SEN UNIV
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