基于图像局部纹理方向概率统计模型的非线性滤波算法

为了更有效地利用图像的局部特征恢复被噪声感染的图像，基于图像局部纹理方向概率统计模型，提出一种针对混合噪声的非线性滤波算法。算法利用Radon变换对图像进行主纹理方向分析,得到图像的局部纹理方向概率密度分布,然后基于概率统计模型，借助中心像素的若干邻近像素对中心像素进行估计，得到中心像素点的灰度值。此算法充分利用了图像的局部特征,既具有良好的去噪能力，又兼顾了对图像细节的保持特性。在处理同时感染脉冲噪声和高斯噪声的混合噪声图像时，算法效果明显优于其他滤波算法。

Nonlinear filtering algorithm based on local texture direction probability statistic model

In order to more effectively make use of local features to restore the noise-infected image, a nonlinear filtering algorithm based on local texture direction probability statistic model was proposed. The proposed algorithm utilizes Radon transform to determine texture direction probability density distribution of local areas of images, and then applies probability statistic model to estimate the middle pixel's gray value according to its neighbour pixels. The performance of the proposed method was evaluated with several sets of images contaminated by pulse noise and Gaussian noise. The experimental results show the superiorities of this method including the abilities of denoising and preserving edges and details of images especially for images with pulse noise and Gaussian noise.