提出了一种基于图像统计信息的去椒盐噪声算法。该方法利用图像中心像素邻域的均值和方差来消除图像中椒盐噪声的影响。首先给出了这种算法的基本原理和实现,然后分别应用中值滤波算法、自适应中值滤波算法以及该算法对有椒盐噪声污染的图像进行滤波,并对实验结果进行比较和分析。实验结果表明,该方法不仅能够消除椒盐噪声,而且能够保持图像的特征信息。最后,对这种算法复杂度也进行了计算分析,并将其和中值滤波算法以及自适应中值滤波算法的复杂度进行了比较,证明该算法比中值滤波算法以及自适应中值滤波算法的复杂度低。
In this paper, a denoising algorithm with image statistical information was proposed. In this method, the mean and variance values of the central pixel and its neighborhood were used to remove the salt and pepper noise on an image. Firstly, the principle of the algorithm and its implementation were presented. This method was compared with the median denoising and the adaptive median denoising methods on images with salt and pepper noise. The experimental results show that the proposed algorithm could eliminate the salt and pepper noise and maintain the characteristics of image. At last, this paper analyzed the computational complexity of the proposed algorithm and compared it with the complexity of the median denoising and the adaptive median denoising algorithms. The computational complexity of the algorithm is also lower than that of the adaptive median denoising.