Normalizing Electrocardiograms of Both Healthy Persons and Cardiovascular Disease Patients for Biometric Authentication

Although electrocardiogram (ECG) fluctuates over time and physical activity, some of its intrinsic measurements serve well as biometric features. Considering its constant availability and difficulty in being faked, the ECG signal is becoming a promising factor for biometric authentication. The majority of the currently available algorithms only work well on healthy participants. A novel normalization and interpolation algorithm is proposed to convert an ECG signal into multiple template cycles, which are comparable between any two ECGs, no matter the sampling rates or health status. The overall accuracies reach 100% and 90.11% for healthy participants and cardiovascular disease (CVD) patients, respectively.