Author(s): Zhao, HZ (Zhao, Hongze); Chen, YF (Chen, Yuanfang); Pei, WH (Pei, Weihua); Chen, HD (Chen, Hongda); Wang, YJ (Wang, Yijun)

Source: EXPERT SYSTEMS WITH APPLICATIONS Volume: 177 Article Number: 114961 DOI: 10.1016/j.eswa.2021.114961 Published: SEP 1 2021

Abstract: Electroencephalogram (EEG)-based biometrics have attracted increasing attention in recent years. A few studies have used visual evoked potentials (VEPs) in EEG biometrics due to their high signal-to-noise ratio (SNR) and good stability. However, a systematic comparison of different types of VEPs is still lacking. Therefore, this study proposes a system framework for VEP-based biometrics. We quantitatively compared the performance of three types of VEP signals in person identification. Flash VEPs (f-VEPs), steady-state VEPs (ss-VEPs), and codemodulated VEPs (c-VEPs) measured from a group of 21 subjects on two different days were used to estimate the correct recognition rate (CRR). We adopted a template-matching-based identification algorithm that was developed for VEP detection in brain-computer interfaces (BCIs) for person identification. Furthermore, this study demonstrates an online person identification system using c-VEPs with a group of 15 subjects. Among the three methods, c-VEPs achieved the highest CRRs of 100% using 3.15-s VEP data (a 5.25-s duration including 2.1-s intervals) in the intra-session condition and 99.48% using 10.5-s VEP data (a 17.5-s duration including 7-s intervals) in the cross-session condition. The online system achieved a cross-session CRR of 98.93% using 10.5-s VEP data (a 14-s duration including 3.5-s intervals). A systematic comparison of the performance of the three types of VEP signals in EEG-based person identification revealed that the c-VEP paradigm achieved the highest CRRs. The online system further demonstrated high performance in practical applications. The proposed VEPbased biometric system obtained promising identification performance, showing great potential for online person identification applications in real life.

Accession Number: WOS:000663299900009

ISSN: 0957-4174

eISSN: 1873-6793

Full Text: https://www.sciencedirect.com/science/article/pii/S0957417421004024?via%3Dihub