一种小波包去噪自适应阈值算法

An Adaptive Threshold Arithmetic for Wavelet Packet De-noising

小波包变换可以将不同频段的信号分离 ,信号和噪声经小波包分解后 ,其小波包系数将表现出不同的特性 ,通过对小波包系数进行阈值处理 ,可以有效地抑制噪声 ,很好地重构信号。运用统计信号处理的理论 ,提出了一种确定小波包分解系数自适应阈值的方法 .结果证明 ,这种方法具有良好的去噪效果 .

Signals may be decomposed into different frequency section by wavelet packet transform method. After wavelet packet decomposition, the properties of the wavelet packet' coefficients of signal and white noise is different. Via thresholding operation in wavelet, noise can be restrained, and signal can be well reconstructed. This paper presents a new method of adaptive filtering via looking for the best threshold in wavelet domain adaptively. The results show that the method can be applied to noise reduction.