Abstract: The nonsubsampled Contourlet transform was used to capture the features such as edge, contour and texture. After that, a weighting function was generated by using the features. Finally, graph regularization equation was used to filter the noisy image. The simulation results show that the proposed method can effectively remove the noise and is superior to other partial differential equation methods.

Key words: image processing, nonsubsampled contourlet transform, graph regularization, graph, partial differential equation

摘要： 用非下采样Contourlet变换提取图像的边缘、轮廓和纹理等具有高维奇异性的特征,并将提取的特征用来构造图的权重函数,用建立在图上的正则化方程实现图像的去噪处理。仿真实验结果表明:该方法能有效地去除图像中的噪声,在去噪性能上优于其他的偏微分方程方法。

关键词: 图象去噪, 非下采样Contourlet, 图正则化, 图论, 偏微分方程