Analysis of denoising on different signals using new thresholding function
Koteswararao Mallaparapu, B. Ananda Krishna, Shaik Masthan, D. Susmitha · 2018
In reality, when the signals either One Dimensional or Two Dimensional are transmitted, they may be corrupted due to noise and at receiver; extraction of our original message is the major task. For example, ECG and EEG biological signals are considered as 1D signal; Lenna and fingerprint images are considered as 2D signals. For the data extraction, many authors proposed various denoising algorithms using threshold functions like hard, soft, garrote and SCAD functions. In this paper, we proposed a wavelet based estimation to remove the noise from the received 1D or 2D signal by calculating threshold value using FDR rule, Visu rule and Top rule. The proposed algorithm is implemented and simulated using MATLAB with the parameters Signal to Noise Ratio (SNR) and Mean Square Error (MSE). From our analysis, it is observed that the mixed function performs better than all existing functions for 1D signal and 2D signals in FDR rule and Visu rule whereas, in top rule, the mixed function performs better only in hard function for both 1D and 2D signals.