基于广义交叉认证的多小波阈值的图像降噪

提出一种新的小波收缩阈值降噪方法，该方法是通过对噪声图像进行多小波变换，然后用广义交叉认证的方法来确定小波阈值参数．由于本文采用的是多小波变换，而多小波一般同时具有正交性和线性相位，另外广义交叉认证方法不需要对噪声的强度进行估计，所以这种方法有比较好的降噪效果．实验结果表明该方法与基于小波变换的广义交叉认证的图像降噪方法相比较，其降噪效果有一定的提高；同时也表明在一定的条件下，其降噪效果要明显好于传统的Wiener滤波方法．

A Multiwavelet Threshold Image Denoising Based on General Cross-Validation

A new image denoising method of multiwavelet shrinkage threshold based on general cross-validation was proposed. The multiwavelet have orthognal and linear phase at the same time, so the multiwavelet transform is used to the image denoising, and the shrinkage parameter is estimated by general cross-validation. The experimental results show that the denoising effect of the proposed method is better than that of wavelet methods based on general cross-validation. Although the denoising effect of this method is worse than that of Wiener filters at low peak-signal-noise ratio, it is better than Wiener filters at high peak-signal-noise ratio.