A new biometric authentication system using heart sounds based on wavelet packet features

In this paper, a new approach for human recognition using heart sounds is proposed. The new approach is based mainly on extracting features from heart sounds using wavelet packet decomposition. Different linear and non-linear filter banks at different decomposition levels are designed using wavelet packet decomposition to select the appropriate bases for extracting discriminant features. Automatic wavelet de-noising and linear discriminant analysis are adopted for pre-processing and classification stages, respectively. The proposed system is tested using an open database for heart sounds known as HSCT-11 which contains data collected from 206 subjects. Based on the achieved results, the proposed system can identify subjects with best accuracy of 91.05% and verify them with an equal error rate of 3.2%. The obtained results in this paper show that wavelet packet based features are appropriate for human recognition task using heart sounds.

I. Introduction

In recent years, biometric authentication systems are becoming increasingly important in many areas like commercial applications, personnel security, military, finance, airport, etc. Commercial biometric authentication systems currently are based on finger-print and facial characteristics. However, these traits are faced with the issue of low security. A fingerprint recognition system can be breached with artificial fingers known as “gummy fingers” [1]. Moreover, face recognition technique can be easily spoofed using printed face models [2]. So, novel biometric traits are being studied to determine their potential in discriminating individuals. One of the most prominent traits is the heart sound signal which is known as Phono-Cardio-Gram (PCG). PCG signals have some advantages, which are not shared by the traditional biometrics. One of these advantages is that they show more security as they are less likely to be artificially generated and fed to a sensor to spoof it. Furthermore, they are easy to process because heart sound is a one dimensional signal with low frequency range and have high universality because every person has a beating heart. In the next paragraph, the PCG time and frequency characteristics are briefly discussed.