摘要
提出了一种通过提升小波变换结合DCT变换的去噪新方法。该算法不依赖于对噪声方差进行估计,直接利用DCT变换对高频各个子带进行局部特征提取,从而估计噪声能量的估计阈值。实验显示,与传统的软、硬阈值去噪算法相比,该算法不仅提高了图像的信噪比,保留了更多的边缘细节,而且处理时间也将近提高一倍,更具有实用价值。
Proposes a new method to perform image de- noising based on lifting wavelet transform and discrete cosine transform（DCT）. Imtead of many algorithms rely on accurate estimation of noise variance, this algorithm estimates noise energy throngh DCT which extracts local feature. Experimental results demonstrate that the proposed method not only achieve better PSNR and retain more edge detail information, but also the process time raises to almost twice as before, it is indeed a good method.
出处
《计算机技术与发展》
2009年第2期62-65,共4页
Computer Technology and Development
基金
国防预研项目
航空科学基金(04D52032)
关键词
图像去噪
提升小波
DCT
image de - noising
lifting wavelet
DCT
