摘要
基于图像小波分解的特点和小波分解后高频小波系数的统计特性,构造了一种新阈值函数的去噪算法。对比传统的硬阈值、软阈值去噪算法,介绍了新阈值函数的原理,推导了算法公式。该阈值函数连续、可导。实验结果表明,利用新阈值函数进行图像去噪,能够有效地抑制图像噪声及马赛克效应。
According to analysis of the properties of wavelet transform and statistical characteristics of wavelet coefficient, this paper proposes a novel wavelet threshold method. Comparing with conventional soft and hard threshold function, the basic principle of this new threshold function is introduced, and the algorithms are deduced. This new threshold function is continual and differentiable. Experimental results show that the denoising algorithm can mitigate the mosaic appearance effectively.
出处
《微电子学与计算机》
CSCD
北大核心
2007年第11期181-182,185,共3页
Microelectronics & Computer
基金
江苏省现代光学技术重点实验室开放课题(KJS02002)
关键词
图像去噪
小波分解
阈值估计
图像处理
image de-noising
wavelet decomposition
threshold estimation
image processing
