由于复数小波变换具有近似平移不变性和良好的方向选择性，因此适用于图像去噪。为了取得更好的降噪效果，提出了一种基于复数小波的高斯尺度混合模型降噪算法。该算法首先对自然图像的复数小波系数建立统计模型，即将位于相邻位置和尺度的系数邻域建模为一个高斯尺度混合模型；然后用该模型对子带系数进行贝叶斯最小均方估计，以达到降低噪声的目的。由于这一模型很好地利用了复数小波系数幅值尺度间和尺度内的相关性，因此可以取得较好的降噪效果。实验结果表明，该算法无论从峰值信噪比还是从主观视觉上都优于一些传统的降噪算法。

In this paper, a new algorithm based on a statistical model of the coefficients of the Dual tree Complex Wavelet Transform (DT CWT) is proposed for image denoising. The DT CWT is approximately shift invariance and has good directionality, which are properties suitable for image de noising. Neighborhoods of coefficients at adjacent positions and scales are modeled as Gaussian Scale Mixture. Under this model, subband coefficients are estimated by Bayesian Least Square estimator. Experimental results show an improved de noising performance of PSNR and human vision in comparison with other methods.