Image denoising method and device based on information distillation network

A network and image technology, applied in the field of image processing, can solve the problems of limited network capacity and time-consuming denoising process, and achieve the effect of improving network capacity, ensuring efficiency, and improving learning speed

Active Publication Date: 2020-02-11
SHENZHEN UNIV
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the embodiments of the present invention is to provide an image denoising method and device based on an information distillation network, which can at least solve the problem that the denoising process of the image denoising network adopted in the related art is time-consuming and the network capacity is relatively limited. question

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 and device based on information distillation network
  • Image denoising method and device based on information distillation network
  • Image denoising method and device based on information distillation network

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0024] In order to solve the technical problems that the denoising process of the image denoising network used in the related technology is time-consuming and the network capacity is relatively limited, this embodiment proposes an image denoising method based on an information distillation network, which is applied to The overall neural network including feature extraction network, information distillation network and compression network, such as figure 1 Shown is a schematic diagram of the network framework of the overall neural network provided in this embodiment, in which A is a feature extraction network, B is an information distillation network, C is a compression network, D is a second-order wavelet transform operation, and I is a second-order wavelet inverse transform Operation, E is the original noise image after the second-order wavelet transform, F is the noise level map.

[0025] Such as figure 2 Shown is a schematic flow chart of the image denoising method provid...

no. 2 example

[0048] In order to solve the technical problems that the denoising process of the image denoising network adopted in the related art is time-consuming and the network capability is relatively limited, this embodiment shows an image denoising device based on an information distillation network, which is applied to The overall neural network including feature extraction network, information distillation network and compression network, please refer to Figure 5 , the image denoising device of this embodiment includes:

[0049] The extraction module 501 is used to perform second-order wavelet transform on the original noise image, and simultaneously input the original noise image after the second-order wavelet transform and the noise level map constructed based on the preset noise threshold to the feature extraction network for preliminary feature extraction. Extracting and processing to obtain a shallow noise feature map; wherein, the original noise image is an image formed afte...

no. 3 example

[0062] This embodiment provides an electronic device, see Figure 6 As shown, it includes a processor 601, a memory 602 and a communication bus 603, wherein: the communication bus 603 is used to realize connection and communication between the processor 601 and the memory 602; the processor 601 is used to execute one or more programs stored in the memory 602 A computer program to implement at least one step in the image denoising method based on the information distillation network in the first embodiment above.

[0063] The present embodiment also provides a computer-readable storage medium, which includes information implemented in any method or technology for storing information, such as computer-readable instructions, data structures, computer program modules, or other data. volatile or nonvolatile, removable or non-removable media. Computer-readable storage media include but are not limited to RAM (Random Access Memory, random access memory), ROM (Read-Only Memory, read-...

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 embodiment of the invention discloses an image denoising method and device based on an information distillation network, and the method comprises the steps: carrying out second-order wavelet transformation of an original noise image, inputting the original noise image and a noise level map into a feature extraction network at the same time, and carrying out the preliminary feature extraction,and obtaining a shallow noise feature map; inputting the shallow noise feature map into an information distillation network for information distillation processing to obtain a deep noise feature map conforming to the noise level of the original noise image; and inputting the deep noise feature map into a compression network to perform color channel compression processing, and then performing second-order wavelet inverse transformation to obtain a noise map for performing image denoising processing on the original noise image. Through the implementation of the invention, the information distillation module is used to obtain rich and more capable features, and the whole network adopts a residual learning mode to improve the learning speed, thereby effectively improving the network capability, and ensuring the efficiency, effectiveness and flexibility of image denoising.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image denoising method and device based on an information distillation network. Background technique [0002] With the rapid development of computer science and image processing technology, images have been widely used in various industries such as medical imaging and face recognition. As one of the underlying tasks of computer vision, image denoising is the basic operation of many computer vision tasks and plays an important role in many aspects. [0003] Currently commonly used image denoising methods can be mainly divided into non-learning-based methods and learning-based methods. Non-learning-based methods include: CBM3D, MCWNNM, etc., while learning-based methods include: DnCNN, FFDNet, etc. , although the above method can meet the needs of image denoising to some extent, but there are still some limitations in practical applications. Among them, the no...

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
CPCG06T5/002G06N3/084G06T2207/10004G06T2207/10024G06T2207/20064G06T2207/20081G06T2207/20084G06N3/045
Inventor 邹文斌扶陈佳卓圣楷金枝李霞
Owner SHENZHEN 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