Feature extraction for human identification based on envelogram signal analysis of cardiac sounds in time-frequency domain

Currently there are many security systems relying on tradition biometrics for the purpose of authorization of legal users into a system. However, traditional biometrics systems which commonly use behavioral biometrics have shown serious drawbacks, violating two of the main requirements of a reliable biometrics, namely permanence and circumvention. The paper explores the effectiveness of the features extracted from the envelogram of joint time-frequency domain of a generic heart sound signal to be used as biometric human identifiers. A powerful signal processing tool, The Wavelet Transform is used to analyze the signal in time-frequency domain and to extract suitable features by with the help of computational software, Matlab.