一种基于纵横子窗口的去椒盐噪声算法

摘要

In order to remove the salt and pepper noise and keep the details of the image effectively,a filter algorithm based on verticalhorizontal sub-windows is proposed.The algorithm detects the center point of the noise image in detection window,if the point is noise,divide the window into 2N sub-windows of vertical and horizontal direction,then compute the non noise points in every sub-window,if their number is odd,calculate their median value,else calculate their mean value,at last,the center point pixel value will be replaced with the median value of these values including all the median value and mean value in the detection window and the center point pixel value.The center pixel value will be retained for the non noise points.The simulation experiment indicates that the algorithm has good robustness and suitability in the noise suppression and image detail protection.%为了有效地去除图像椒盐噪声并且较好地保持图像的细节,提出了纵横子窗口的滤波算法.算法对噪声图像检测窗口内中心像素点进行检测,如果是噪声点,将检测窗口划分为水平和垂直方向2N个子窗口,计算子窗口内非噪声点的个数,如果为奇数,求出它们的中值;如果为偶数,求出它们的均值,然后用这些子窗口的中值、均值及中心点像素值的中值替代中心点像素值,对于非噪声点的中心点保持原值不变.仿真实验表明,算法对椒盐噪声的抑制和图像细节的保持具有较好的鲁棒性和适应性.