基于信号分析的椒盐噪声滤波算法

Removal of Salt and Pepper Noise Based on the Signal Analysis Algorithm

椒盐噪声对图像造成或亮或暗的像素点,从视觉上影响图像的质量。采用基于信号分析的方法去除图像中的椒盐噪声,信号分析能准确判断出噪声与信号像素,该方法依据椒盐噪声模型准确区分信号与噪声,对信号像素给予保留,而对于噪声像素则有针对性地对其作中值滤波、扩大的中值滤波或均值滤波。实验结果表明,与线性加权、梯度倒数加权以及小波去噪算法相比,文中算法能有效降低图像中的椒盐噪声,对图像的边缘与细节保持较好,并且能得到较高的信噪比。

Signal analysis can accurately distinguish between corrupted pixels and signal pixels.A new denoising algorithm is proposed based on the signal analysis.This method which aimed at denoising the image with salt and pepper noise effectively combines the signal analysis,media filter,enlarged median filter and mean filter.Median filters can preserve the details,while mean filters can smooth the noise well.Experimental results show that this algorithm can eliminate salt and pepper noise and gives significantly better image quality than other algorithms such as linear weighted filter,gradient inverse weighted filter and the wavelet denoising.With the analysis of the experimental data,this method reaches a good result not only the details and edge information of the original image but also the PSNR.