An improved two-dimensional multi-level median filtering algorithm

The traditional 2-D MLM is often used to protecting images´ details, but the algorithm is weak when it is used to suppress image noise particularly image noise with rich details. In order to prove this problem, this paper proposes an improved 2-D MMF algorithm which the number of basic sub-windows is 6 while the number of basic sub-windows is 4 in the traditional 2-D MLM, make sure every pixel can contribute to median value. After done a series of experiments using a set of rich details´ fingerprint images in this paper, the results conducted that the ability to protect details in this algorithm almost equal to the traditional two-dimensional multi-level median filter, but the ability to suppress noise in this algorithm is much better than in the traditional one.