Abstract:
This paper presents a feature extraction method known as Pulse Active Harmonic (PAH) implemented on electrocardiograph (ECG) signals for biometric authentication. The technique is based on a pulse width modulation concept. A total of 200 ECGs from 100 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. This work shows that: a) the PAH method outperforms conventional temporal feature extraction techniques, b) its performance is comparable to other, previously introduced, Pulse Active based methods. Hence, owing to their close similarities Pulse Active approaches can readily be combined to form robust and inherently secure biometric authentication systems
