Image denoising method based on generative adversarial networks

A network and image technology, applied in the field of computer vision, to achieve the effect of uniform distribution

Inactive Publication Date: 2018-11-06
DALIAN UNIV OF TECH
View PDF4 Cites 90 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still deficiencies in the restoration of image texture details. In order to improve image

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 based on generative adversarial networks
  • Image denoising method based on generative adversarial networks
  • Image denoising method based on generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] The denoising of X-ray imaging images is the experimental goal. The experimental platform GPU is NVIDIA GeForce GTX TITANX, and the operating environment is Ubuntu14.04, Python3.4, Tensorflow0.12.1.

[0087] Step 1. Obtain an X-ray imaging picture I, where the pixel gray levels of I range from 0 to 255.

[0088] Step 2. Establish a noise-free image library, and use 500 grayscale images of 180×180 pixel size in the LSUN data set in the network as the experimental data set.

[0089] Step 3. The images in the data set are divided into 98000 image blocks through a sliding window with a step size of 10.

[0090] Step 4, adding Gaussian noise with an intensity of 0 to 50 to the image block to train the noise discrimination network.

[0091] Step 5: Add noise of a certain intensity to the image block to train the generative confrontation network, and save the network parameters corresponding to the noise.

[0092] Step 6. Change the added noise intensity, and repeat step 5 ...

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 provides an image denoising method based on generative adversarial networks, and belongs to the technical field of computer vision. The method comprises the following steps: (1) designing a neural network for estimation for noise intensity of an image containing noises; (2) using image blocks in an image library to add noises of the intensity according to the estimated noise intensity to use the same as samples of training the networks; (3) in network training, designing a new generation network and discrimination network, and adopting a form of fixing the generation network to train the discrimination network and fixing discrimination network parameters to train the generation network to enable the networks to carry out adversarial training; and (4) using the trained generation network as a denoising network, and selecting a network parameter according to a result, which is obtained by the noise recognition network, to denoise the image containing the noises. The methodhas the effects and the advantages that a visual effect of the denoised image is improved without the need for manual intervention for adjusting the parameter, and texture details of the image can bebetter restored.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to an image denoising method based on a generative confrontation network. Background technique [0002] In the process of image acquisition and transmission, image noise will be generated. When collecting images, the photoelectric conversion of the device will introduce noise; when the image is transmitted, channel noise will also interfere with the image, so the image quality is often degraded. The noise in the image will make the information contained in the image uncertain, making it impossible for people to recognize and understand the image well. In the field of computer vision, when performing operations such as image recognition and segmentation, image noise will cause serious deviations in the processing results. In the military and medical fields, errors caused by such deviations can be costly. Therefore, the method of image denoising has important research signifi...

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
CPCG06T5/002G06T2207/20081G06T2207/20084
Inventor 孙怡张元祺
Owner DALIAN 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