张祎俊,
练秋生,
1.燕山大学信息科学与工程学院 秦皇岛 066004
2.河北省信息传输与信号处理重点实验室 秦皇岛 066004
基金项目:国家自然科学基金(61471313)，河北省自然科学基金(2019203318)
详细信息
作者简介:陈书贞：女，1968年生，副教授，研究方向为图像处理、压缩感知、深度学习、相位恢复
张祎俊：女，1994年生，硕士生，研究方向为深度学习，JPEG压缩伪迹去除
练秋生：男，1969年生，教授，博士生导师，研究方向为稀疏表示、深度学习、压缩感知及相位恢复
通讯作者:练秋生 lianqs@ysu.edu.cn
中图分类号:TN911.73计量
文章访问数:3335
HTML全文浏览量:1182
PDF下载量:57
被引次数:0
出版历程
收稿日期:2018-10-15
修回日期:2019-03-05
网络出版日期:2019-04-02
刊出日期:2019-10-01
JPEG Compression Artifacts Reduction Algorithm Based on Multi-scale Dense Residual Network
Shuzhen CHEN,Yijun ZHANG,
Qiusheng LIAN,
1. Institute of Information Science and Technology, Yanshan University, Qinhuangdao 066004, China
2. Hebei Key Laboratory of Information Transmission and Signal Processing, Qinhuangdao 066004, China
Funds:The National Natural Science Foundation of China (61471313), The Natural Science Foundation of Hebei Province (2019203318)
摘要
摘要:JPEG在高压缩比的情况下，解压缩后的图像会产生块效应、边缘振荡效应和模糊，严重影响了图像的视觉效果。为了去除JPEG压缩伪迹，该文提出了多尺度稠密残差网络。首先把扩张卷积引入到残差网络的稠密块中，利用不同的扩张因子，使其形成多尺度稠密块；然后采用4个多尺度稠密块将网络设计成包含2条支路的结构，其中后一条支路用于补充前一条支路没有提取到的特征；最后采用残差学习的方法来提高网络的性能。为了提高网络的通用性，采用具有不同压缩质量因子的联合训练方式对网络进行训练，针对不同压缩质量因子训练出一个通用模型。经实验表明，该文方法不仅具有较高的JPEG压缩伪迹去除性能，且具有较强的泛化能力。
关键词:JPEG压缩/
压缩伪迹/
多尺度稠密块/
扩张卷积
Abstract:In the case of high compression rates, the JPEG decompressed image can produce blocking artifacts, ringing effects and blurring, which affect seriously the visual effect of the image. In order to remove JPEG compression artifacts, a multi-scale dense residual network is proposed. Firstly, the proposed network introduces the dilate convolution into a dense block and uses different dilation factors to form multi-scale dense blocks. Then, the proposed network uses four multi-scale dense blocks to design the network into a structure with two branches, and the latter branch is used to supplement the features that are not extracted by the previous branch. Finally, the proposed network uses residual learning to improve network performance. In order to improve the versatility of the network, the network is trained by a joint training method with different compression quality factors, and a general model is trained for different compression quality factors. Experiments demonstrate that the proposed algorithm not only has high JPEG compression artifacts reduction performance, but also has strong generalization ability.
Key words:JPEG compression/
Compression artifacts/
Multi-scale dense blocks/
Dilate convolution
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=4aa7c246-ebfd-4e75-a1e9-e453c008c400
