一种新的基于脉冲噪声点检测的自适应中值滤波算法

A new adaptive median filter algorithm based on detection of impulse noise points

传统的中值滤波算法在去除脉冲噪声时会造成图像细节信息的丢失,从而使图像变得模糊,提出一种新的基于脉冲噪声点检测的自适应中值滤波算法.该算法先检测出脉冲噪声点,采用自适应窗口对噪声点进行中值滤波.仿真实验表明,与传统中值滤波相比,这种新算法很好地保留了图像的细节,提高了峰值信噪比.

Median filter is a nonlinear filtering technique widely used for removal of impulse noise. Despite its effectiveness in noise smoothing, this traditional median filter algorithm tends to remove fine details when it is applied to an image, resulting in a fuzzy one. Therefore, a new adaptive median filter algorithm was proposed based on detection of impulse noise points. By using this algorithm, the impulse noise points were detected first, and then median filter with adaptive window was applied to the points to filter them off. Simulation experiments showed that compared with traditional median filter, the details of images was retained and the ratio of peak signal to noise increased when the new algorithm was used.