基于L~1范数变分模型的高密度椒盐噪声滤波

针对现有图像滤波算法在去除高密度椒盐噪声方面的不足,提出了一种基于L1范数变分模型的去噪算法.该算法首先根据椒盐噪声的特点和像素的局部灰度特征分离出噪声点和信号点,在滤波过程中,对信号点不予处理,而对噪声点采用基于L1范数的变分模型进行恢复.由于椒盐噪声的灰度值与原始像素无关,因此,去噪时只利用噪声点邻域内信号点本身的灰度信息,并将已处理过的噪声点当作新的信号点,以避免对下一像素滤波时的影响.最后通过仿真实验,结果表明,在高密度噪声条件下(50%),该算法的噪声去除能力和细节保护能力均可获得令人满意的结果.

Image Filtering Algorithm for High Density Salt-and-Pepper Noise Based on L1 Norm Variational Model

The major drawback of recent image filtering algorithms is lack of the ability of removing high density salt- and- pepper noise. To alleviate this limitation, a new denoising algorithm based on L1 norm variational model was proposed. Firstly, according to the characteristics of salt--and--pepper noise and local grayscale feature of pixels, this algorithm separates noise points and signal points. The signal points were not treated during the filtering process, while the noise points were recovered by theL1 norm variational model. We do not use the grayscale information of noise point itself to remove noise because the gray value of salt--and--pepper noise is not related to the original pixel. Meanwhile by transforming the noise points into signal points we could avoid the noise spreading in the neighborhood. The experimental results show that the proposed algorithm has the ability of removing noises and preserving the partial details of images in comparison with some recent methods when the noise density is very high （〉50%）.