一种改进的自适应保细节中值滤波算法

The Improved Adaptive Minutiae Preserving Median Filter

中值滤波是常用的降噪算法，它可以保留比较尖锐的边界，但是却容易模糊图象的细节。尽管已经有一些改进算法，但效果并不十分理想。文章介绍了一种保细节中值滤波算法，采用了多尺度多方向的窗口，根据图象各部分特性自适应地选择窗口进行中值滤波。实验结果证明，文章的算法优于其他几种常用的中值滤波算法。

Median filter is a widely used and effective nonlinear filter in image processing. However,it can not be ignored that median filter blurs the minutiae such as points and short and thin lines. Although there're several improved median smoothers,the results are not satisfying. In this paper,we propose an improved adaptive median filter using multiscale and multidirectional window. This method,to some extent,is effective for both smoothing and minutiae preserving, mainly because it selects different window according to the feature of different part of the image. Compared with other methods,this algorithm has better performance.