摘要
比较了小波变换和曲波变换,指出小波变换只具有点状奇异性的不足之处和曲波变换具有多尺度各向奇异性的优点,分析了现有的基于曲波变换的图像去噪方法,并对目前基于曲波变换的去噪算法进行了改进,提出结合Wrapping和Cycle Spinning的WCSCurvelet去噪新算法。仿真实验的结果证实了该算法减少了伪Gibbs现象,较好地保留了图像的细节和纹理,获得了更好的视觉效果和更高的峰值信噪比。
The comparison between wavelet transform and Curvelet transform indicates that wavelet transform only has dot singularity and Curvelet transform has advantage of multi-scale singularity in each direction. After analyzing the method of image denoising by Curvelet transform, the paper proposed a new method of combining wrapping and cycle spinning Curvelet transform to improve the existing algorithm. According to the simulation experiment, the results of the denoised pictures show that the improved algorithm has reduced the pseudo-Gibbs phenomena, can reserve more detailed information, texture of images and get higher visual impression and PSNR value.
出处
《计算机应用》
CSCD
北大核心
2009年第10期2665-2667,共3页
journal of Computer Applications
基金
国家自然科学基金资助项目(70533050)
关键词
阈值
小波变换
曲波变换
循环平移
图像去噪
threshold: wavelet transform
Curvelet transform
cycle spinning
image denoising