一种改进的自适应中值滤波算法研究

Research on Improved Adaptive Median Filter Algorithm

中值滤波被广泛地应用于消除图像的脉冲噪声(椒盐噪声),但去噪后的图像容易出现失真,且当噪声密度大于0.5时中值滤波基本失效。针对自适应中值滤波去除高密度脉冲噪声效果并不理想的问题,提出了基于阈值的自适应中值滤波算法。首先,该算法充分利用当前像素点的灰度值与邻域像素点的灰度值之间的关系,通过自适应处理求出相应的阈值;其次,利用像素最大最小和阈值的关系对噪声点和信号点进行区分;最后采用不同的方法对噪声点和信号点进行去噪处理,从而实现对脉冲噪声的滤除。

Median filter is widely applied to eliminate image impulse noise, but after filtering the image distortion will occur.The median filter did not work when the noise density is greater than 0.5.The adaptive median filter do not perform well in case of high density uniformly distributed salt pepper noise,so based on threshold of new improved adaptive median filter is presented.The improved adaptive median filter makes full use of the relationship between the gray value of the current pixel and the gray values of the neighborhood pixels.It calculates the corresponding threshold by adaptive processing.