基于AI深度学习的老电影散斑噪声智能修复方法

Yu Zheng, Jiandong Cui, H. Zhong, Dong-Hyuk Choi
{"title":"基于AI深度学习的老电影散斑噪声智能修复方法","authors":"Yu Zheng, Jiandong Cui, H. Zhong, Dong-Hyuk Choi","doi":"10.1109/icaice54393.2021.00019","DOIUrl":null,"url":null,"abstract":"Speckle noise in old movies is caused by erasure or other reasons, which affects the quality of video images. Therefore, an intelligent repair method of speckle noise in old movies based on AI deep learning is proposed. Based on the analysis of the characteristics of speckle noise in old films, the image noise is filtered by bilateral filtering, and the image features are obtained by combining a convolution neural network to obtain the perceptual loss data. On this basis, the jump connection is added to the deep learning network structure of image restoration. Taking the loss function as the training object, the high-quality restoration of speckle noise is realized by optimizing the loss function. The test results show that the design method can ensure that the average PSNR value of the repaired image can reach more than 40 under lower and shorter training iterations, and the effect is obvious.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Intelligent Repair Method of Old Movie Speckle Noise Based on AI Deep Learning\",\"authors\":\"Yu Zheng, Jiandong Cui, H. Zhong, Dong-Hyuk Choi\",\"doi\":\"10.1109/icaice54393.2021.00019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Speckle noise in old movies is caused by erasure or other reasons, which affects the quality of video images. Therefore, an intelligent repair method of speckle noise in old movies based on AI deep learning is proposed. Based on the analysis of the characteristics of speckle noise in old films, the image noise is filtered by bilateral filtering, and the image features are obtained by combining a convolution neural network to obtain the perceptual loss data. On this basis, the jump connection is added to the deep learning network structure of image restoration. Taking the loss function as the training object, the high-quality restoration of speckle noise is realized by optimizing the loss function. The test results show that the design method can ensure that the average PSNR value of the repaired image can reach more than 40 under lower and shorter training iterations, and the effect is obvious.\",\"PeriodicalId\":388444,\"journal\":{\"name\":\"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)\",\"volume\":\"40 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/icaice54393.2021.00019\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/icaice54393.2021.00019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

老电影中的斑点噪声是由于擦除或其他原因造成的,影响视频图像的质量。为此,提出了一种基于AI深度学习的老电影散斑噪声的智能修复方法。在分析老电影中散斑噪声特征的基础上,通过双边滤波对图像噪声进行滤波,结合卷积神经网络获得图像特征,得到感知损失数据。在此基础上,在图像恢复的深度学习网络结构中加入跳转连接。以损失函数为训练对象,通过对损失函数进行优化,实现高质量的散斑噪声恢复。测试结果表明,该设计方法能保证在较低较短的训练迭代下,修复后图像的平均PSNR值能达到40以上,效果明显。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Intelligent Repair Method of Old Movie Speckle Noise Based on AI Deep Learning
Speckle noise in old movies is caused by erasure or other reasons, which affects the quality of video images. Therefore, an intelligent repair method of speckle noise in old movies based on AI deep learning is proposed. Based on the analysis of the characteristics of speckle noise in old films, the image noise is filtered by bilateral filtering, and the image features are obtained by combining a convolution neural network to obtain the perceptual loss data. On this basis, the jump connection is added to the deep learning network structure of image restoration. Taking the loss function as the training object, the high-quality restoration of speckle noise is realized by optimizing the loss function. The test results show that the design method can ensure that the average PSNR value of the repaired image can reach more than 40 under lower and shorter training iterations, and the effect is obvious.
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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信