基于自适应非局部均值滤波的图像去块算法

摘要/Abstract

摘要：

针对传输和存储中原始图像被JPEG和MPEG等标准进行压缩而产生的块效应，提出了一种图像去块算法.该算法选取非局部均值滤波作为框架，并通过机器学习来确定和优化参数，使得非局部均值滤波可以做到自适应处理.结果表明，该算法去块效果优于目前最新的形状自适应滤波法和维纳滤波法.

关键词: 自适应均值滤波, 去块, 机器学习

Abstract:

Common image compression standards such as JPEG and MPEG can lead to blocking artifacts which causes serious image degradation. In this paper, a non-local means filter for deblocking was proposed and its parameters were adaptively optimized by machine learning. The experimental results prove that the proposed algorithm constantly outperforms the peer ones on all kinds of images.

Key words: adaptive non-local means filter, deblocking, machine learning

中图分类号:

TP 30

刘书，王慈. 基于自适应非局部均值滤波的图像去块算法[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1930-1933.

LIU Shu,WANG Ci. Image Deblocking with Adaptive Non-local Means Filter[J]. Journal of Shanghai Jiaotong University, 2013, 47(12): 1930-1933.

参考文献

［1］谢强, 郑世宝, 于晓静 . 一种结合H.264/AVC CABAC熵编码器特征的视频选择性内容加密算法［J］. 上海交通大学学报, 2008,42(10): 17621766.

XIE Qiang, ZHENG Shibao, YU Xiaojing. A selective video content encryption algorithm exploiting the characteristics of H. 264/AVC CABAC entropy encoder［J］. Journal of Shanghai Jiaotong University, 2008, 42(10): 17621766.

［2］李焱淼，张永良，黄亚平，等.基于频域分析的联指图前后背景分离算法［J］.上海交通大学学报，44（8）：10891093.

LI Yanmiao, ZHANG Yongliang, HUANG Yaping, et al. Background removing of slap fingerprint images based on frequency domain analysis［J］. Journal of Shanghai Jiaotong University, 2010, 44(8): 10891093.

［3］Jagroop S, Sukhwinder S, Dilbag S, et al. Detection method and filters for blocking effect reduction of highly compressed images［J］. Signal Processing: Image Communication, 2011, 26(8):493506.

［4］XING Lili,CHANG Qianshun,QIAO Tiantian.The algorithms about fast nonlocal means based image denoising［J］. Acta Mathematicae Applicatae Sinica, 2012, 28(2): 247254.

［5］Sun D, Cham W K. Postprocessing of low bitrate block DCT coded images based on a fields of experts prior［J］. IEEE Trans Image Process, 2007,16(11): 27432751.

［6］Averbuch A Z, Schclar A, Donoho D L. Deblocking of block transform compressed images using weighted sums of symmetrically aligned pixels［J］. IEEE Transactions on Image Processing, 2005, 14(2): 200212.

［7］Zhang M, Gunturk B K. Multiresolution bilateral filtering for image denoising［J］. IEEE Transactions on Image Processing, 2008, 17(12): 23242333.

［8］Nath V K, Hazarika D, Mahanta A. Blocking artifacts reduction using adaptive bilateral filtering［J］. International Conference on Signal Processing and Communications, 2010(2):15.

［9］Chatterjee P, Milanfar P. Patchbased nearoptimal image denoising［J］. IEEE Transactions on Image Processing,20122, 21(4): 16351649.

［10］Buades A, Coll B, Morel J M. A nonlocal algorithm for image denoising［J］. Computer Vision and Pattern Recognition, 2005(2): 6065.

［11］de Queiroz R L. Processing JPEGcompressed images and documents［J］. IEEE Trans Image Processing, 1998, 7: 16611672.

［12］Robertson M A, Stevenson R L. DCT quantization noise in compressed images［J］. Int Conf Image Process, 2001(1): 185188.

［13］ZHAI Guangtao, ZHANG Wenjun, YANG Xiaokang, et al. Efficient deblocking with coefficient regularization, shapeadaptive filtering, and quantization constraint［J］. IEEE Trans Multimedia, 2008, 10(5): 735745.

[1]	贾岛, 陈磊, 朱志鹏, 余曜, 迟德建. 机器学习在引战系统设计中的应用研究[J]. 空天防御, 2022, 5(2): 27-31.
[2]	王卓鑫, 赵海涛, 谢月涵, 任翰韬, 袁明清, 张博明, 陈吉安. 反向传播神经网络联合遗传算法对复合材料模量的预测[J]. 上海交通大学学报, 2022, 56(10): 1341-1348.
[3]	李川, 聂熠文, 刘军伟, 孟凡钦, 沈晓静. 基于机器学习的多算法融合航迹稳健起始方法[J]. 空天防御, 2022, 5(1): 20-24.
[4]	周毅, 秦康平, 孙近文, 范栋琦, 郑义明. 台风气象环境电网设备风险量化预警及其N-m故障处置预案在线生成方法[J]. 上海交通大学学报, 2021, 55(S2): 22-30.
[5]	何夏维, 蔡云泽, 严玲玲. 一种合成残差式的反作用轮故障检测方法[J]. 上海交通大学学报, 2021, 55(6): 716-728.
[6]	祝颂, 钱晓超, 陆营波, 刘飞. 基于XGBoost的装备体系效能预测方法[J]. 空天防御, 2021, 4(2): 1-.
[7]	包清临, 柴华奇, 赵嵩正, 王吉林. 采用机器学习算法的技术机会挖掘模型及应用[J]. 上海交通大学学报, 2020, 54(7): 705-717.
[8]	化存卿. 物联网安全检测与防护机制综述[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1307-1313.
[9]	屠恩美，杨杰. 半监督学习理论及其研究进展概述[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1280-1291.
[10]	刘凯a，张立民b，周立军a. 随机受限玻尔兹曼机组设计[J]. 上海交通大学学报（自然版）, 2017, 51(10): 1235-1240.
[11]	王进，张军，胡白帆. 结合最优类别信息离散的细粒度超网络微阵列数据分类[J]. 上海交通大学学报（自然版）, 2013, 47(12): 1856-1862.