改进贝叶斯阈值的Contourlet域图像去噪方法  

Contourlet Domain Image Denoising Method with Improved Bayesian Threshold

作　　者：许亚男[1] 钱叶旺[1] 王鞠庭 XU Yanan;QIAN Yewang;WANG Juting(Chizhou University,School of Mechanical and Electrical Engineering,Chizhou 247000,Chin幼)

机构地区：[1]池州学院机电工程学院,安徽池州247000

出　　处：《新乡学院学报》2020年第6期42-45,共4页Journal of Xinxiang University

基　　金：安徽省高校自然科学重点项目(KJ2016A515);池州学院自然科学研究重点项目(2017ZRZ007)。

摘　　要：图像经Contourlet变换后,可以获得更多的方向信息,重构后可以更好地表达图像的轮廓信息。含噪图像经过非下采样Contourlet(NSCT)分解可得到尺度、方向均不同的系数,对这些系数分别进行不同阈值去噪。实验结果表明:利用改进后的BayesShrink阈值对NSCT分解后的各层各方向系数去噪,可获得更好的视觉效果,提高信噪比和边缘保持度。After the image is transformed by Contourlet,more direction information can be obtained,and the contour information of the image can be better expressed after reconstruction.After non-subsampled Contourlet transform(NSCT)decomposition of noisecontaining images,coefficients with different scales and directions were obtained.These coefficients were denoised by different threshold values.The experimental results show that the improved BayesShrink threshold can be used to denoise the coefficients of each layer and each direction after NSCT decomposition,better visual effects can be obtained,and the signal-to-noise ratio and edge retention can be improved.

关 键 词：CONTOURLET NSCT 阈值去噪 BayesShrink 

分 类 号：TN911[电子电信—通信与信息系统]