EEG-based biometry using steady state visual evoked potentials

Abstract

The use of brain signals for person recognition has in recent years attracted considerable interest because of the increased security and privacy these can offer when compared to conventional biometric measures. The main challenge lies in extracting features from the EEG signals that are sufficiently distinct across individuals while also being sufficiently consistent across multiple recording sessions. A range of EEG phenomena including eyes open and eyes closed activity, visual evoked potentials (VEPs) through image presentation, and other mental tasks have been studied for their use in biometry. On the other hand, the use of steady state visual evoked potentials (SSVEPs), distinctly from VEPs, has barely been explored for person identification, and the stability of features extracted from SSVEP signals over multiple sessions has never been assessed in the context of a biometric identification system. In this work we investigate the reliability of SSVEP features as a biometric measure. Specifically we assess the performance of SSVEP features for the identification of eight participants across multiple recording sessions. The proposed system was tested using distinct enrollment and testing sessions. An overall true acceptance rate of 91.7% and an overall false acceptance rate of 1% were obtained. This performance is comparable and in some cases even better than the performance reported for other EEG biometric modalities tested under similar conditions.