Creating and sharing knowledge for telecommunications

Realtime Electrocardiogram Segmentation For Finger Based ECG Biometrics

Lourenço, A. ; Silva, H. ; Lourenço, R. L. ; Leite, P. L. ; Fred, A. L. N.

Realtime Electrocardiogram Segmentation For Finger Based ECG Biometrics, Proc International Conf. on Bio-inspired Systems and Signal Processing - Biosignals - INSTICC, Vilamoura, Portugal, Vol. ?, pp. ? - ?, February, 2012.

Digital Object Identifier:

In Electrocardiographic (ECG) based biometric recognition there are two main approaches for ECG feature extraction: fiducial and non-fiducial. Fiducial methods use points of interest within single heartbeat waveforms, obtained by segmenting the ECG signal using QRS complexes. In this paper we study several QRS detection algorithms with the puropose of determining what is the best algorithm in the context of finger based ECG biometrics using fiducial approaches; our main focus is on real-time calculation of single heart beats. We propose a method combining the adaptative characteristics of Christov Algorithm, with the strategy of Englese and Zeelenberg algorithm. Obtained results on real data show that online approaches are competitive with offline versions, and represent a contribution for the realization of real-time biometric recognition.