基于纹理细节方向性的混合滤波器加速算法

Accelerated Algorithm of a Mixed Filter Based on Directional Texture and Detail

提出一种基于纹理细节方向性的混合噪音滤波器加速算法(DMNF)。针对混合滤波器(MNF)存在着较大的计算负担问题提出一种加速算法,该算法在计算相似窗口相似程度时,只允许相似窗口中处于0°、45°、90°、135°方向上的像素参与其加权"范数"计算,而忽略其它方向上的像素。以此提高滤波速度。仿真实验证明,DMNF算法在保持MNF的滤波效果的基础上,对各种噪音类型,运算速度均可提高25%以上。

A mixed noise filter acceleration algorithm （DMNF） base on directional texture and detail is proposed, which is the accelerated algorithm for the mixed noise filter （MNF） and the existence of a large computing burden. It only allows similar window at 0 °, 45 °, 90 °, 135 ° direction of pixels involved in the calculation of the weighted ＇ norm＇, while ignoring the other direction of the pixels, in the calculation of the similarity degree of a similar window. Therefore, it can improve the filtering speed. Simulation experiments show, for a variety of noise types, on the basis of keeping filtering effect of MNF, DMNF＇ s filtering speed can be increased by more than twenty-five percent.