基于直方图的自适应高斯噪声滤波器

图像滤噪时,利用原图像的信息越多滤波效果越好,但这通常是不可行的或不可能的。为此提出了一种图像恢复的新方法。该方法通过输入图像估计出原图像的直方图,并从该直方图得到一个包含原图像信息的模糊隶属度函数,以此隶属度函数构建一个模糊加权平均滤波器。该滤波器能够根据图像区域特性差异及噪声强弱自适应地采用不同的滤波尺度。实验结果表明,该滤波器滤波效果优于传统的滤波器和其它模糊滤波器,特别是当噪声发生概率超过0 3时,其滤波效果更加明显。

Adaptive filter for removing image Gauss noise based histogram

The more information of original image is used in removing image noise, the better will the effect of filter be, but this is usually impossible or impracticable. In the light of this we present a novel approach for image restoration. The approach estimates histogram of original image through input image to get a membership that contains information of original image through this histogram, then a weighted fuzzy mean filter is established by this membership. Meanwhile, the filter can adopt different filter scale in adaptive mode in the light of character divergence of image region and intensity of noise. Experimental results show that the filter gives superior performance compared with conventional filters and other fuzzy filter, especially, the superiority will more obvious when noise probability exceeds 0.3.;