BIOMETRIC IDENTIFICATION BASED ON FREQUENCY ANALYSIS OF CARDIAC SOUNDS

The performance of traditional biometric identification systems is as yet unsatisfactory in certain fields of application. For this reason other physiological or behavioural characteristics are recently being considered using new electrical or physical signals linked to a person's vital signs. This paper examines the biometric characteristics of PCG (PhonoCardioGram) signals from cardiac auscultation. The idea is that PCG signals have specific individual characteristics that can be taken into consideration as a valid physiological sign used in a biometric system. The paper proposes an automatic system for the identification of individuals via frequency analysis of cardiac sound. The results obtained confirm the biometric properties of PCG signals, which can thus be included among the physiological signs used by an automatic identification system.