基于Contourlet变换自适应阈值的图像去噪算法  

Image De-Noising Algorithm Using Adaptive Threshold Based on Contourlet Transform

作　　者：戴维[1] 于盛林[1] 孙栓[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016

出　　处：《电子学报》2007年第10期1939-1943,共5页Acta Electronica Sinica

基　　金：江苏省自然科学基金(No.BK2001047);航空科学基金(No.04D52032)

摘　　要：综合利用Contourlet变换和图像在各个尺度各个方向上的轮廓细节的大小,一定程度上改进了Donoho阈值"过扼杀"其分解系数的缺点,同时还考虑图像的轮廓细节.实验结果表明,与小波阈值,Contourlet阈值和多尺度Contourlet阈值相比,这两种方法更好的提取了图像的轮廓细节,提高了图像的PSNR值.A new method for image de-noising which colligated the strong point of Contourlet transform and the magnitude of the detail of image in every scale and direction. This paper deals with the problem of snuffing out the Contourlet coefficients to exceed, and it also can solve the problem of taking no consideration of image details. Experiment on image de-noising shows that： compare to the wavelet threshold, Contourlet threshold and multi-scale threshold using Contourlet transform, the two methods both pick up the image detail better and improve the peak signal-to-noise ratio.

关 键 词：图像去噪 CONTOURLET变换 小波变换 萎缩阈值 

分 类 号：TN911.73[电子电信—通信与信息系统]