模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (11): 990-1003    DOI: 10.16451/j.cnki.issn1003-6059.202111003
Deep Learning Design and Application Current Issue| Next Issue| Archive| Adv Search |
Image Dehazing Based on Generative Adversarial Network
HUANG Shuying1, WANG Bin2, LI Hongxia2, YANG Yong3, HU Wei3
1. School of Computer Science and Technology, Tiangong University, Tianjin 300387
2. School of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang 330013
3. School of Information Management, Jiangxi University of Finance and Economics, Nanchang 330032

Download: PDF (5484 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Compared with the image dehazing methods based on image enhancement or physical model, the current image dehazing methods based on deep learning improve the computational efficiency to a certain extent. Nevertheless, the problems of incomplete dehazing and color distortion still exist in complex scenes. Aiming at the different perceptions of human eyes on global and local features, an algorithm of image dehazing based on generative adversarial networks is proposed. Firstly, a multi-scale generator network is designed. The full-size image and the segmented image block are taken as the input to extract the global contour information and local detail information of the image. Then, a feature fusion module is constructed to fuse the global and local information, and the authenticity of the generated dehazing image is judged by the discriminant network. To make the generated dehazing image closer to the corresponding real haze-free image, a multivariate joint loss function is designed by combining the dark channel prior loss, the adversarial loss, the structural similarity loss and the smooth L1 loss to train the network. Experimental results show that the proposed algorithm is superior to some state-of-the-art dehazing algorithms.
Key wordsImage Dehazing      Generative Adversarial Networks(GAN)      Multi-scale Structure      Dark Channel Prior      Multivariate Joint Loss     
Received: 10 May 2021     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.61862030,62072218), Natural Science Foundation of Jiangxi Province(No.20192ACB20002,20192ACBL21008)
Corresponding Authors: YANG Yong, Ph.D., professor. His research interests include image processing and deep learning.   
About author:: HUANG Shuying, Ph.D., associate professor. Her research interests include image processing and machine learning.
WANG Bin, master student. His research interests include deep learning, low-quality image enhancement and image dehazing.
LI Hongxia, master student. Her research interests include image dehazing and low-light image enhancement.
HU Wei, master student. His research interests include image dehazing and image enhancement.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
HUANG Shuying
WANG Bin
LI Hongxia
YANG Yong
HU Wei
Cite this article:   
HUANG Shuying,WANG Bin,LI Hongxia等. Image Dehazing Based on Generative Adversarial Network[J]. , 2021, 34(11): 990-1003.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202111003      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I11/990
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn