基于双树复小波变换的信号去噪算法

Signal Denoising Algorithm Based on Dual-tree Complex Wavelet Transform

为了提高接收信号的质量,在一定程度上消除噪声对信号的影响,提出了一种基于双树复小波变换的信号降噪方法。通过双树结构消除了因间隔采样而丢失的有用信息,对每一层的高频分量的实部和虚部分别计算阈值,依据各自的阈值进行滤波处理。实验结果表明:该方法与离散小波变换消噪方法相比具有平移不变性,处理后的波形较平滑,能够较好地保留信号细节信息,而且其去噪性能也优于离散小波变换。

To improve the quality of received signal and eliminate the influence of noise on the signal,a signal denoising algorithm based on Dual-Tree Complex Wavelet Transform（DTCWT）is proposed. Through the double tree structure,the loss of useful information resulting from the sampling is avoided,and then the threshold of real part and imaginary part of high frequency component for each floor is calculated separately,and filter processing according to their respective threshold. Simulation results show that this algorithm has the translation invariance compared with the Discrete Wavelet Transform （DWT）denoising algorithm,and the waveform is not only relatively smooth and keeps the details of the signal better after processing,but also denoising performance is superior to the DWT.