基于分层噪声估计的Bayesian-NSCT图像去噪算法

A Bayesian-NSCT Image Denoising Arithmetic Based on Layered Noise Estimation

非抽样Contourlet(NSCT)是一种具有平移不变特性的Contourlet变换,能更好地表示图像几何纹理信息。本文提出了一种在非抽样Contoulet域下基于域分层噪声估计的,采用Bayes自适应阀值计算和硬阀值去噪相结合的的综合图像去噪算法。实验结果表明,该方法改善了噪声图像的去噪效果,保存了图像中更多有效信息,性能和视觉效果均优于其他同类算法。

The non-subsampled Contourlet transform （NSCT）, which is a shift-invariant version of the Contourlet transform,could capture the intrinsic geometrical structure of image. This paper proposes a Nonsubsampled Contourlet domain image denoising integrated approach based on stratified noise estimates and adaptive Bayes threshold with hard-thresholding ruetion. Experiments resluts shows that the mathod can improve the denoised image performance, reseving more effective information of image and having better performance and visual effect than similar arithmetics.