二级椒盐噪声检测的极值滤波算法

Extreme Values Filtering Algorithm of Secondary Salt-and-Pepper Noise Detection

为准确检测图像中的椒盐噪声并滤除,提出了一种基于极值的二级噪声检测滤波算法。该算法根据椒盐噪声的特点,确定了准噪声点的范围,把准噪声点和信号点分类。为了找出准噪声点中被误判的信号点,在图像的8个纹理方向上分别应用了极值噪声检测,根据中心像素点被判为极值的次数分离出信号点和噪声点;对噪声点,取滤波窗口内的信号点的中值进行滤波。试验结果表明:该算法对椒盐噪声有很好的抑制作用。

In order to accurately detect and filter salt-and-pepper noise in an image,an algorithm of secondary noise detection and filtering based on extreme values is proposed.The algorithm sets the range of the noise point according to the salt-and-pepper noise characteristics,and separates the quasi-noise and signal points.To identify the signal points misjudged as quasi-noise,noise detection based on extreme values is applied in eight texture directions.From the frequency of the center pixel being judged as an extreme,it can be classified as signal or noise,and the noise pixel is substituted by the median of the signal in the filter window.Experimental results show that the algorithm can effectively suppress salt-and-pepper noise.