使用离散余弦变换和条件生成对抗网络的微光图像恢复

IF 3.9 4区 物理与天体物理 0 OPTICS
Banglian Xu, Yao Fang, Zhixiang Bian, Yu Huang, Yaoyao Tan, Xue, Cheng, Jiale Song, Leihong Zhang
{"title":"使用离散余弦变换和条件生成对抗网络的微光图像恢复","authors":"Banglian Xu, Yao Fang, Zhixiang Bian, Yu Huang, Yaoyao Tan, Xue, Cheng, Jiale Song, Leihong Zhang","doi":"10.3116/16091833/22/4/225/2021","DOIUrl":null,"url":null,"abstract":". In the process of low-light imaging, some part of useful information of an image is overwhelmed by a noise. When interference is large, the signal-to-noise ratio (SNR) detected in a system is reduced to a very low level. We study the low-light imaging under condition when the detection SNR is equal to 1 dB. Taking into account that the noise is often located in the high-frequency spectral part, we use discrete cosine transform (DCT) to remove the noise or, at least, filter out its some part. Then we use an algorithm of conditional generative adversarial network (CGAN) to improve the image quality. The simulation results testify that the DCT and CGAN algorithms combined together improve significantly the restoration results and the final quality of images. The latter is high enough, with the average peak SNR being higher than 22 dB and the structural similarity index measure amounting to about 0.8.","PeriodicalId":23397,"journal":{"name":"Ukrainian Journal of Physical Optics","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Low-light image restoration using discrete cosine transform and conditional generative adversarial network\",\"authors\":\"Banglian Xu, Yao Fang, Zhixiang Bian, Yu Huang, Yaoyao Tan, Xue, Cheng, Jiale Song, Leihong Zhang\",\"doi\":\"10.3116/16091833/22/4/225/2021\",\"DOIUrl\":null,\"url\":null,\"abstract\":\". In the process of low-light imaging, some part of useful information of an image is overwhelmed by a noise. When interference is large, the signal-to-noise ratio (SNR) detected in a system is reduced to a very low level. We study the low-light imaging under condition when the detection SNR is equal to 1 dB. Taking into account that the noise is often located in the high-frequency spectral part, we use discrete cosine transform (DCT) to remove the noise or, at least, filter out its some part. Then we use an algorithm of conditional generative adversarial network (CGAN) to improve the image quality. The simulation results testify that the DCT and CGAN algorithms combined together improve significantly the restoration results and the final quality of images. The latter is high enough, with the average peak SNR being higher than 22 dB and the structural similarity index measure amounting to about 0.8.\",\"PeriodicalId\":23397,\"journal\":{\"name\":\"Ukrainian Journal of Physical Optics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ukrainian Journal of Physical Optics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.3116/16091833/22/4/225/2021\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ukrainian Journal of Physical Optics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.3116/16091833/22/4/225/2021","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

摘要

。在微光成像过程中,图像中部分有用信息被噪声掩盖。当干扰较大时,系统中检测到的信噪比(SNR)降低到很低的水平。研究了检测信噪比为1 dB条件下的弱光成像。考虑到噪声通常位于高频频谱部分,我们使用离散余弦变换(DCT)来去除噪声或至少滤除其某些部分。然后,我们使用条件生成对抗网络(CGAN)算法来提高图像质量。仿真结果表明,DCT和CGAN算法相结合可以显著提高图像的恢复效果和最终质量。后者足够高,平均峰值信噪比高于22 dB,结构相似指数测度约为0.8。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Low-light image restoration using discrete cosine transform and conditional generative adversarial network
. In the process of low-light imaging, some part of useful information of an image is overwhelmed by a noise. When interference is large, the signal-to-noise ratio (SNR) detected in a system is reduced to a very low level. We study the low-light imaging under condition when the detection SNR is equal to 1 dB. Taking into account that the noise is often located in the high-frequency spectral part, we use discrete cosine transform (DCT) to remove the noise or, at least, filter out its some part. Then we use an algorithm of conditional generative adversarial network (CGAN) to improve the image quality. The simulation results testify that the DCT and CGAN algorithms combined together improve significantly the restoration results and the final quality of images. The latter is high enough, with the average peak SNR being higher than 22 dB and the structural similarity index measure amounting to about 0.8.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
9.90
自引率
0.00%
发文量
20
审稿时长
>12 weeks
期刊介绍: “Ukrainian Journal of Physical Optics” contains original and review articles in the fields of crystal optics, piezo-, electro-, magneto- and acoustooptics, optical properties of solids and liquids in the course of phase transitions, nonlinear optics, holography, singular optics, laser physics, spectroscopy, biooptics, physical principles of operation of optoelectronic devices and systems, which need rapid publication. The journal was founded in 2000 by the Institute of Physical Optics of the Ministry of Education and Science of Ukraine.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信