One of the most interesting problems in denoising of images includes despeckling of multiplicative noise. This paper proposes a novel statistical processor in the framework of Non-sub Sampled Shearlet Transform (NSST) to reduce the effect of the multiplicative noise on images given preserving of structural and visual quality of image. First, we indicate that NSST coefficients of logarithmically transformed images can be statistically meaningful modeled by t-location scale (TLS). For designing our processor, we employ Minimum Mean Squared Error (MMSE) estimator to reduce noise distortion. We show by using TLS as the prior distribution, non-linear noise suppression behavior is obtained in test images. Finally, we compare our method by the state-of-the-art algorithms like soft and hard thresholding and also with well-known adaptive filters in this area like Wiener, Frost, Lee and one recent method in shearlet denoising framework.

图像去噪中最有趣的问题之一是对乘法噪声进行去斑点。本文提出了一种在非子采样的Shearlet变换（NSST）框架下的新型统计处理器，以在保持图像的结构和视觉质量的情况下减少乘法噪声对图像的影响。首先，我们表明对数变换后的图像的NSST系数可以通过t位置尺度（TLS）进行统计学上有意义的建模。为了设计处理器，我们采用最小均方误差（MMSE）估计器来减少噪声失真。我们显示通过使用TLS作为先验分布，可以在测试图像中获得非线性噪声抑制行为。最后，