Random Interpolation Average Using Lifting Scheme for Signal Denoising

In order to improve the denoising effectiveness of the random interpolation average (RIA) scheme, the lifting scheme was applied for signal denoising in this paper. The proposed method can obtain satisfying denoised results and keep the computational load at a proper level. Numerical results showed that the process in this paper supplies the best signal-to-noise ratio (SNR) and root of mean square error (RMSE). In comparison to the classical wavelet transforms (WT), the conventional lifting scheme (LS), and the fully translation-invariant (TI) scheme, the RIA scheme has shown a significant improvement in the average signal-to-noise ratio (SNR) of denoised signals, with increases of 3.21 dB, 3.82 dB, and 0.68 dB, respectively. According to the visual results, the singular points of four signals can be kept very well without introducing considerable distortion.