基于变分自编码器(CA-VAE)方法的对比注意增强单幅图像去雾

IF 1.3 Q3 ENGINEERING, MULTIDISCIPLINARY
Sandeep Vishwakarma, Anuradha Pillai, Deepika Punj
{"title":"基于变分自编码器(CA-VAE)方法的对比注意增强单幅图像去雾","authors":"Sandeep Vishwakarma, Anuradha Pillai, Deepika Punj","doi":"10.33889/ijmems.2023.8.4.042","DOIUrl":null,"url":null,"abstract":"Hazy images and videos have low contrast and poor visibility. Fog, ice fog, steam fog, smoke, volcanic ash, dust, and snow are all terrible conditions for capturing images and worsening color and contrast. Computer vision applications often fail due to image degradation. Hazy images and videos with skewed color contrasts and low visibility affect photometric analysis, object identification, and target tracking. Computer programs can classify and comprehend images using image haze reduction algorithms. Image dehazing now uses deep learning approaches. The observed negative correlation between depth and the difference between the hazy image’s maximum and lowest color channels inspired the suggested study. Using a contrasting attention mechanism spanning sub-pixels and blocks, we offer a unique attention method to create high-quality, haze-free pictures. The L*a*b* color model has been proposed as an effective color space for dehazing images. A variational auto-encoder-based dehazing network may also be utilized for training since it compresses and attempts to reconstruct input images. Estimating hundreds of image-impacting characteristics may be necessary. In a variational auto-encoder, fuzzy input images are directly given a Gaussian probability distribution, and the variational auto-encoder estimates the distribution parameters. A quantitative and qualitative study of the RESIDE dataset will show the suggested method's accuracy and resilience. RESIDE’s subsets of synthetic and real-world single-image dehazing examples are utilized for training and assessment. Enhance the structural similarity index measure (SSIM) and peak signal-to-noise ratio metrics (PSNR).","PeriodicalId":44185,"journal":{"name":"International Journal of Mathematical Engineering and Management Sciences","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Enhancement in Single-Image Dehazing Employing Contrastive Attention over Variational Auto-Encoder (CA-VAE) Method\",\"authors\":\"Sandeep Vishwakarma, Anuradha Pillai, Deepika Punj\",\"doi\":\"10.33889/ijmems.2023.8.4.042\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Hazy images and videos have low contrast and poor visibility. Fog, ice fog, steam fog, smoke, volcanic ash, dust, and snow are all terrible conditions for capturing images and worsening color and contrast. Computer vision applications often fail due to image degradation. Hazy images and videos with skewed color contrasts and low visibility affect photometric analysis, object identification, and target tracking. Computer programs can classify and comprehend images using image haze reduction algorithms. Image dehazing now uses deep learning approaches. The observed negative correlation between depth and the difference between the hazy image’s maximum and lowest color channels inspired the suggested study. Using a contrasting attention mechanism spanning sub-pixels and blocks, we offer a unique attention method to create high-quality, haze-free pictures. The L*a*b* color model has been proposed as an effective color space for dehazing images. A variational auto-encoder-based dehazing network may also be utilized for training since it compresses and attempts to reconstruct input images. Estimating hundreds of image-impacting characteristics may be necessary. In a variational auto-encoder, fuzzy input images are directly given a Gaussian probability distribution, and the variational auto-encoder estimates the distribution parameters. A quantitative and qualitative study of the RESIDE dataset will show the suggested method's accuracy and resilience. RESIDE’s subsets of synthetic and real-world single-image dehazing examples are utilized for training and assessment. Enhance the structural similarity index measure (SSIM) and peak signal-to-noise ratio metrics (PSNR).\",\"PeriodicalId\":44185,\"journal\":{\"name\":\"International Journal of Mathematical Engineering and Management Sciences\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2023-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Mathematical Engineering and Management Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.33889/ijmems.2023.8.4.042\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Mathematical Engineering and Management Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33889/ijmems.2023.8.4.042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

模糊图像和视频对比度低,能见度差。雾、冰雾、蒸汽雾、烟雾、火山灰、灰尘和雪都是拍摄图像的糟糕条件,会使颜色和对比度变差。由于图像的退化,计算机视觉应用经常失败。模糊图像和视频与扭曲的色彩对比和低能见度影响光度分析,目标识别和目标跟踪。计算机程序可以使用图像雾霾减少算法对图像进行分类和理解。图像去雾现在使用深度学习方法。观察到的深度与模糊图像的最大和最低颜色通道之间的差异呈负相关,这启发了我们的研究。使用跨子像素和块的对比注意机制,我们提供了一种独特的注意方法来创建高质量的无雾图像。提出了L*a*b*颜色模型作为图像去雾的有效颜色空间。基于变分自编码器的除雾网络也可用于训练,因为它压缩并尝试重建输入图像。估计数百个影响图像的特性可能是必要的。在变分自编码器中,直接给出模糊输入图像的高斯概率分布,由变分自编码器估计其分布参数。对该数据集的定量和定性研究将显示该方法的准确性和弹性。live的合成和真实单幅图像去雾示例子集被用于训练和评估。改进了结构相似度指标(SSIM)和峰值信噪比指标(PSNR)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An Enhancement in Single-Image Dehazing Employing Contrastive Attention over Variational Auto-Encoder (CA-VAE) Method
Hazy images and videos have low contrast and poor visibility. Fog, ice fog, steam fog, smoke, volcanic ash, dust, and snow are all terrible conditions for capturing images and worsening color and contrast. Computer vision applications often fail due to image degradation. Hazy images and videos with skewed color contrasts and low visibility affect photometric analysis, object identification, and target tracking. Computer programs can classify and comprehend images using image haze reduction algorithms. Image dehazing now uses deep learning approaches. The observed negative correlation between depth and the difference between the hazy image’s maximum and lowest color channels inspired the suggested study. Using a contrasting attention mechanism spanning sub-pixels and blocks, we offer a unique attention method to create high-quality, haze-free pictures. The L*a*b* color model has been proposed as an effective color space for dehazing images. A variational auto-encoder-based dehazing network may also be utilized for training since it compresses and attempts to reconstruct input images. Estimating hundreds of image-impacting characteristics may be necessary. In a variational auto-encoder, fuzzy input images are directly given a Gaussian probability distribution, and the variational auto-encoder estimates the distribution parameters. A quantitative and qualitative study of the RESIDE dataset will show the suggested method's accuracy and resilience. RESIDE’s subsets of synthetic and real-world single-image dehazing examples are utilized for training and assessment. Enhance the structural similarity index measure (SSIM) and peak signal-to-noise ratio metrics (PSNR).
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
3.80
自引率
6.20%
发文量
57
审稿时长
20 weeks
期刊介绍: IJMEMS is a peer reviewed international journal aiming on both the theoretical and practical aspects of mathematical, engineering and management sciences. The original, not-previously published, research manuscripts on topics such as the following (but not limited to) will be considered for publication: *Mathematical Sciences- applied mathematics and allied fields, operations research, mathematical statistics. *Engineering Sciences- computer science engineering, mechanical engineering, information technology engineering, civil engineering, aeronautical engineering, industrial engineering, systems engineering, reliability engineering, production engineering. *Management Sciences- engineering management, risk management, business models, supply chain management.
×
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