ECG feature extraction via waveform segmentation

The analysis of the ECG signal is widely used for detecting a variety of cardiac pathologies. Most of the clinically useful information embedded in the ECG is related to the duration and amplitude of its individual components. Producing algorithms for the automatic extraction of the ECG features is complicated due to the time-varying nature of the signal resulting of variable physiological conditions and the presence of noise. This paper presents an algorithm for detecting the individual components of the ECG signal. First the R wave is precisely detected using wavelets, and then the other ECG features are extracted using a waveform segmentation approach. The algorithm was tested on the QT Database.