中文摘要：

提出了一种基于噪声估计的自适应开关型中值滤波器（IASMNE，improved adaptive switching median filter based on noise estimation）。IASMNE以图像经小波变换后在不同尺度和不同方向提取的子带滤波系数值的统计信息构成刻画图像受噪声干扰程度的特征矢量，在大量噪声图像上获得的特征矢量为学习数据集，并利用支持向量回归（SVR）分析实现对图像中噪声比例的准确估计。基于此，IASMNE对高、中、低不同噪声比例图像启动不同的滤波策略，并灵活设置滤波参数。大量实验表明，与其它开关型滤波器相比，IASMNE能够合理地根据图像噪声干扰程度进行最佳滤波，尤其是对于大于70％的椒盐噪声（SPN）能够大幅度提高图像质量。

英文摘要：

Digital images are often corrupted by impulse noise during image acquisition, recording and transmission, and the corrupted digital images badly inhibit subsequent image processing operations, So determining the noise ratio is very important for optimizing the operating parameters of a denoising illter. In this paper,an improved adaptive switching median filter based on noise ration estimation （IAS- MNE） is proposed. The sub-band coefficients of an image obtained from a wavelet transform over three scales and three orientations are parameterized using a generalized Gaussian distribution （GGD） and these estimated parameters are used to form feature vector describing image noise level. Given a lot of image feature vectors obtained from training and test distorted images, we use support vector regression （SVR） to predict noise ratio of an image. Based on the predicted noise ratio, we use different filtering policies and filtering parameters, which are adaptively set, to obtain optimal computational efficiency and filtering quality. Experimental results show that the proposed filer can effectively remove the impulse noise and provide better performance than many existing impulse denoising filters with a wide range （from 10% to 90%） of noise corruption in terms of peak signal-to-noise ratio （PSNR）, especially for those more than 70% high density impulse noise.