一种基于非下采样Contourlet变换的去噪算法

A Denoising Algorithm Based on Non Sampling Contourlet Transform

文章提出了一种新的去噪算法,算法是基于非下采样Contourlet变换(NSCT)的自适应阈值。首先需要对含噪图像进行非下采样Contourlet变换,然后得到各个尺度各个方向子带的系数。为了克服软、硬阈值函数的缺点,提出了一种自适应的新阈值函数。仿真实验表明,文章方法在峰值信噪比(PSNR)、信噪比(SNR)、均方误差(MSE)与视觉效果上均优于其他去噪算法。

In this paper, a new denoising algorithm is proposed, which is based on the adaptive threshold of the non sampling Contourlet transform （NSCT）. Firstly, we need to carry out the non sampling Contourlet transform for the noisy images, and then get the coefficients of the different directions of each direction., In order to overcome the shortcoming of the soft and hard threshold function, a new adaptive threshold function is proposed.. The simulation results show that the method of the method is superior to the other denoising algorithms in the peak signal-to-noise ratio （PSNR）, SNR （SNR）, mean square error （MSE） and visual effect.