HeartID: Cardiac biometric recognition

This letter examines the applicability of cardiac signals for biometric recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The recognition performance, tested over 21 subjects, is very promising.