Signal Denoising Using Double Density Discrete Wavelet Transform

Abstract

Reality signals do not exist without noise. Wavelet transform based denoising seem to be a powerful tool for suppressing noise in signals. In this paper, we investigate the using of double density discrete wavelet transform "DD-DWT" which based on one scaling function and two wavelet functions, for signal denoising and comparing its performance with the traditional DWT. Three groups of additive White Gaussian Noise levels (5 dB, 3 dB, 2 dB) are added to some standard test signals with both hard and soft threshold function to evaluate the performance of each method in term of Root Mean Square Error (RMSE) and Signal to Noise Ratio (SNR). Experiment results show that DD-DWT performs better than traditional DWT in both RMSE and SNR especially at low SNR.