基于模糊转换的图像椒盐噪声检测和去除

为了去除椒盐噪声,提高图像的质量,提出了一种基于模糊转换的加权均值方法来有效的对图像中的噪声进行抑制,主要包含两个阶段:噪声检测和噪声去除。在噪声检测阶段,首先将不含噪声的像素点与可能为噪声的像素点(像素取最大值或最小值)区分开来,对于后者,提出了一种相邻处理过点的绝对差分和方法对其是否为噪声进行进一步判别,并引入两个预定的阈值,将可能为噪声的像素点划分为3类:无噪声点、轻度噪声点和重度噪声点;在噪声去除阶段,一种D8距离相关的模糊转换加权均值滤波方法被提出对噪声进行有效的去除。仿真结果表明,与一些现存方法相比,提出的方法较好的去除了椒盐噪声,并且在去除噪声的同时较好的保持了图像的细节信息,无论是峰值信噪比(PSNR)还是结构相似度(SSIM)都有了较大的提高。和实验效果与其最接近的自适应加权均值滤波相比,提出方法节省了超过65%的运行时间。

Image salt and pepper noise detection and removal based on fuzzy switching

In order to remove salt-and-pepper noise, a novel fuzzy switching adaptive weighted mean filter is proposed to eliminate the noise effectively.The method includes two stages: noise detection and noise elimination.In the first stage, first pixels are differentiated into two kinds: noiseless pixels and possible noise pixels.For the second kind pixels, we use the method of the sum of absolute luminance difference with processed pixels next to it and introduce two thresholds to divide them into three categories, noiseless pixels, lightly corrupted pixels and heavily corrupted pixels.In the second stage, a D8 distance relevant fuzzy switching adaptive weighted mean filter is proposed to remove salt-and-pepper noise.The simulation results show that compared with some existing methods, our method can effectively eliminate salt-and-pepper noise, the results contain more details, and have higher values of two typical image quality metrics: peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).Our method saves over 65% processing time compared with the adaptive weighted mean filter, which has the most similar results.