A Statistical Approach to Biometric Identity Verification Based on Heart Sounds

Author

Beritelli, Francesco ; Spadaccini, Andrea

Author_Institution

Dipt. di Ing. Inf. e delle Telecomun., Univ. of Catania, Catania, Italy

fYear

2010

fDate

18-25 July 2010

Firstpage

93

Lastpage

96

Abstract

One of the most recent innovations in the field of biometric recognition is the usage of heart sounds as physiological traits for identity verification. In this paper, we propose a statistical approach, supported by Gaussian Mixture Models, to the the problem of biometric identity verification based on heart sounds. The system is validated on a database of heart sounds acquired from 147 people, and shows a significant performance improvement with respect to other approaches, yielding an Equal Error Rate of 15.53%.

Keywords

Gaussian processes; acoustic signal processing; biometrics (access control); cardiology; pattern recognition; security of data; Gaussian mixture model; biometric identity verification; digital heart sound analysis; physiological trait; statistical approach; Biological system modeling; Databases; Error analysis; Feature extraction; Heart; Speaker recognition; Training; Gaussian Mixture Models; biometric recognition; digital heart sounds analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Security Information Systems and Technologies (SECURWARE), 2010 Fourth International Conference on

Conference_Location

Venice

Print_ISBN

978-1-4244-7517-9

Electronic_ISBN

978-0-7695-4095-5

Type

conf

DOI

10.1109/SECURWARE.2010.23

Filename

5633628