Analysis Of Signal Denoising Methods Based On Wavelet Transform
The real world signals do not exist without noise. Wavelet Transform based denoising is a powerful method for
suppressing noise in signals. In this paper, signal denoising based on Double-Density Discrete Wavelet Transform
(DDDWT) and Dual-Tree Discrete Wavelet Transform (DTDWT) methods are implemented with optimum values of
threshold point and level of decomposition. Based on the intensity of noise in the received signal, optimum values of
threshold point and level of decomposition are determined. The results in terms of Root Mean Square Error (RMSE) and
Signal to Noise Ratio (SNR) are then compared with the corresponding values of Discrete Wavelet Transform (DWT) based
denoising method. The popular test signal; piece-regular contaminated with Additive White Gaussian Noise (AWGN) is
chosen for the implementation. The results of MATLAB simulations show that for the selected threshold point and level of
decomposition, the DDDWT and DTDWT perform better than the DWT method.
Keywords: Signal Denoising, Discrete Wavelet Transform, Double- Density Discrete Wavelet Transform, Dual-Tree
Discrete Wavelet Transform, Root mean square error.