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

Image defogging method based on generative confrontation network

A generative, network technology, applied in the field of image processing, can solve problems such as image contrast reduction, color shift, detail loss, etc., to enhance robustness, solve large space and time complexity, and reduce deviation from reality. the effect of the situation

Active Publication Date: 2018-10-02
NANJING UNIV OF INFORMATION SCI & TECH
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The technical problem to be solved by the present invention is to provide an image defogging method based on a generative adversarial network, which can solve the problems of image contrast reduction, partial detail defect and color shift in the scene to a certain extent, and also solves the problem of algorithm The question of scope

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 defogging method based on generative confrontation network
  • Image defogging method based on generative confrontation network
  • Image defogging method based on generative confrontation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] like Figure 4 As shown, an image defogging method based on a generative confrontation network includes the following steps:

[0044] (1) Convert the image into a grayscale image of x, y, z;

[0045] (2) Standardize the gamma space and color space: (firstly, the entire image needs to be normalized (normalized). In the texture intensity of the image, in order to reduce the local surface exposure, the local shadow and illumination changes of the image are reduced through compression processing; ) Gamma compression formula is as follows:

[0046] I(x,y)=I(x,y) gamma (1)

[0047] (For example, Gamma=1 / 2 can be taken;)

[0048] (3) Calculate the image gradient: Convolute the original image with the [-1,0,1] gradient operator to obtain the gradient component gradscalx in the x direction (horizontal direction, with the positive direction to the right), and then use [1 ,0,-1] T The gradient operator performs convolution operation on the original image to obtain the gradi...

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 defogging method based on a generative confrontation network. An HOG feature extraction mode and a priori information-added denoising mode are adopted, a loss functionbased on changes of environmental haze concentration data is proposed, a solution which is the best on the whole is thus selected, problems of color offset and the like can be solved to a large extent, excessive image defogging is also prevented, a balance is searched as much as possible between getting clear results and reducing complexity, and the problem that prior information constrains an algorithm application scope is solved to a certain degree.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image defogging method based on a generative confrontation network. Background technique [0002] With the continuous development of information technology and the popularization of electronic equipment, people enjoy life more and more, and at the same time record life through photos. With the advancement and development of deep neural networks, people began to apply deep neural networks to solve various image problems, such as image completion, image removal of rain and snow, etc. Due to the intensification of smog in recent years, good photos are also affected by the low visibility caused by smog. Therefore, image defogging algorithms such as dark channel prior and maximum contrast are introduced. Since Goodfellow proposed a generative confrontation network in 2014, GAN (Generative Adversarial Network) has been favored by scholars because of its sharper and cleare...

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): G06T5/00G06T5/40
CPCG06T5/40G06T2207/20081G06T2207/20084G06T5/73
Inventor 田青林鹏石玥于丹丹王超
Owner NANJING UNIV OF INFORMATION SCI & 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