基于相关性阈值的NSCT图像去噪方法研究

利用非下采样Contourlet变换(NSCT)平移不变性、多分辨率、多方向的优点,提出一种基于尺度相关与阈值去噪相结合的非下采样Contourlet变换图像去噪方法。首先对噪声图像进行非下采样Contourlet变换,得到各个尺度各个方向子带的系数,然后采用相关系数归一的方法,结合Bayesian自适应阈值来达到更好的去噪效果。仿真实验表明,该方法在提高去噪后图像的峰值信噪比的同时,有效保留了图像的纹理信息,避免伪吉布斯现象,改善了图像的视觉效果。

NSCT Image Denoising Method Based on Combination of Scale Correlation and Threshold

Utilizing the advantages of translation invariance,multi-resolution,multi direction of non subsampled contourlet transform（NSCT）,this paper proposed a denoising method based on combination of NSCT sale correlation and threshold denoising.First,a noisy image is non-subsampled Contourlet transformed,each scale and individual subband coefficients are obtained,then using the normalized correlation coefficient method combined with Bayesian adaptive threshold denoising,a better image denosing result is achieved.The simulation results show that Peak Signal to Noise Ratio（PSNR） is increased in the image after denoising,image texture information is preserved effectively,pseudo-Gibbs artifacts are avoided,and the visual effect of images is improved at the same time.