自适应型中心加权的中值滤波器

Adaptive center-weighted median filter

针对低噪声污染的图像提出了一种改进型中值滤波算法.该算法是一种自适应型中心加权的高效中值滤波算法.通过粗略地检测图像中的冲击噪声污染率,来自适应地调整中心像素的权值,从而控制新的滤波器对不同污染程度的噪声图像进行不同程度的平滑,即对轻度污染的图像进行轻度的平滑,而对污染比较严重的图像进行重度的平滑.实验结果表明,新的滤波算法优于传统的中值滤波器及其他一些典型的改进型中值滤波器.

An improved median filter was introduced to suppress impulsive noise with low contamination ratios. The proposed solution was a class of adaptive center-weighted median filter. By roughly estimating the corruption ratio, the proposed filter adaptively determines the central weight to make sure that it could perform different amount of smoothing for noisy images with different contamination ratios, namely it could perform slight smoothing for slightly corrupted images and more smoothing for heavily corrupted images. The experimental results show that the proposed solution significantly outperforms the standard median filter （SMF） and some other typical improved median filters.