小波域Wiener滤波器的设计

讨论了基于小波的阈值去噪方法和Wiener滤波方法在信号去噪中的应用.其中,小波阈值去噪方法在许多信号空间上是近似最优的,而Wiener滤波方法是最小均方误差意义上的最优估计.在小波阈值去噪方法和经验Wiener滤波器基础上,设计了一种小波域Wiener滤波器.仿真结果表明:文中提出的方法在均方误差和峰值信噪比性能两方面均优于传统的小波阈值去噪方法.同时指出了进一步改善去噪效果的一种有效途径.

Design of Wiener Filter in Wavelet Domain

The paper discussed the application of wavelet based thresholding denoising and Wiener filtering for removal of noise in signal. Wavelet based thresholding denoising method is nearly optimal in many signal spaces. But the Wiener filter is optimal for any signal in the sense of MMSE. A Wiener filter in wavelet domain is designed by combining the characteristics of the both approaches. Simulation results showed that the proposed method outperformed the traditional wavelet thresholding method in terms of mean squared error and peak signal-to-noise ratio. An effective way to improve the denoising ability of Wiener filter in wavelet domain is also addressed.