中文摘要：

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．

英文摘要：

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.