一种快速去除高密度椒盐噪声的滤波算法

为了更好地恢复被高密度椒盐噪声污染的图像,在传统的自适应中值滤波算法的基础上提出了一种改进的自适应滤波算法。该算法将3×3矩形滤波窗口内极值点视为可疑噪声点,对可疑噪声点自适应调节滤波窗口大小进一步判断是否为噪声点;将噪声点区分为低密度噪声区噪声点和高密度噪声区噪声点,并分别用改进后的中值滤波算法、自适应修正后均值滤波算法处理,信号点保持不变。仿真结果表明,该算法处理速度快并且能够有效恢复被椒盐噪声(密度达80%)污染的图像,在去噪的同时能够很好地保护图像的细节。

One Fast Filter Algorithm for the Removal of High-Density Salt and Pepper Noise

An improved adaptive median filter has been proposed based on the traditoinal adaptive median filter to recover the imgage polluted by the salt-and-pepper noise with high density. This method views the extreme gray level in 3×3 rectangular filter window as an suspicious noise pixels,adaptively adjust the window size to judge whether the suspicious noise pixels is a noise pixels.Divie the noise pixels into a low density region and a high density region, the noise pixels were processed with the improved median filter and the improved adaptive mean filters respectively ,but the signal pixels remain invariable. The simulation results showed that the proposed algorithm is quickly in processe and can not only effectively restore the image polluted by salt- and- pepper noise with density of 80%,but also can well preserve the image details.