Ajou University repository

Design of CycleGAN model for SAR image colorization
Citations

SCOPUS

0

Citation Export

Publication Year
2021-08-01
Journal
17th IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2021 - Proceedings
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
17th IEEE VTS Asia Pacific Wireless Communications Symposium, APWCS 2021 - Proceedings
Keyword
colorizationCycleGANmachine learningSAR
Mesh Keyword
ColorizationCycleganDesigned modelsHigh-resolution imagesImage colorizationsImages processingLimited resolutionNetwork modelsSARSAR Images
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsComputer Science ApplicationsSignal Processing
Abstract
In deep learning based image processing, the number of dataset is important to train the designed model. However, it is hard to secure SAR images, because satellite-based SAR is limited and high-resolution images are very expensive. Generative adversarial network (GAN) supplements this problem by learning two models, generator and discriminator, in an adversarial process at the same time. In this paper, we take one dataset as input data, and compare its accuracy using GAN models. CycleGAN is used to generate images among GAN models. Optical images are used for dataset and Chinese cities are selected for SAR images. The lack of dataset, a drawback of SAR images, is supplemented using data augmentation. SSIM, MSE, and PSNR of fake and original images are calculated using dataset and show that CycleGAN has the most lower MSE with 639.4379 and highest PSNR with 20.0728. Pix2pix has the most highest SSIM with 0.7842.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36667
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85116667414&origin=inward
DOI
https://doi.org/10.1109/apwcs50173.2021.9548749
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=9548745
Type
Conference
Funding
ACKNOWLEDGMENT This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2021-2018-0-01424) supervised by the IITP(Institute for Information & communications Technology Promotion)
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Kim, Jae-Hyun Image
Kim, Jae-Hyun김재현
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.