ECG Baseline Wander Removal with Recovery of the Isoelectric Level

Baseline wander removal is an unavoidable step in ECG signal processing. The in-band nature of this noise makes its removal difficult without affecting the ECG. Many approaches have been proposed in the literature. Among them, cubic spline interpolation is the only one able to recover the isoelectric level in the detrended signal. However it exhibits poor detrending performance. In this paper we extend our recent approach based on the notion of quadratic variation reduction, to address the problem of recovery of the isoelectric level. This is achieved by constraining the amplitude of few fiducial points to lie on isoelectric segments. Conversely to cubic spline interpolation, which requires a fiducial point for each beat, the proposed approach requires very few points: as few as one single point is sufficient. Simulation results show that the proposed approach largely outperforms cubic spline interpolation, being very effective in removing baseline wander and recovering the isoelectric level, while preserving ECG morphology.