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.
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 pro- posed 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.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2013年第12期1930-1933,共4页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金资助项目(60902072)
教育部博士点新教师基金项目(20090073120030)
关键词
自适应均值滤波
去块
机器学习
adaptive non-local means filter
debloeking
machine learning
