三种空间域图像去噪方法的比较与研究

Comparison and Research on Three Image De-noising Methods Based on Spatial Domain

去噪是图像处理中极其重要的步骤,包括空间域去噪和变换域去噪两种。均值滤波、中值滤波和维纳滤波是三种最重要的空间域去噪方法,它们在去除高斯噪声、椒盐噪声和泊松噪声中的性能表现不同,模板尺寸是影响其性能的一个重要因素。实验表明,三种去噪方法在去除不同噪声时都能找到一个最佳模板尺寸,维纳滤波适用于去除高斯噪声和泊松噪声,中值滤波适用于去除椒盐噪声。

De-noising is a very important step in image processing,including two kinds of methods which are based on spatial domain and transform domain.Average filtering,median filtering and wiener filtering are three most important De-noising methods based on spatial domain,whose performance is different in filtering Gauss noise,salt and pepper noise and Poisson noise,one important factor affecting the performance is the size of template.Experiments show that a template of optimal size can be found for each de-noising methods in filtering the different image noise,wiener filtering is suitable for filtering Gauss noise and Poisson noise,and the median filtering suits to filter salt and pepper noise.