Person Identification Using Evoked Potentials and Peak Matching

In this paper, we explore visually evoked potentials (VEPs) as a potential tool for biometric identification. Using a clinical stimulation paradigm, single channel pattern onset VEPs are recorded from raw EEG from 10 healthy male subjects aged between 20 and 24. Following this, two feature extraction techniques are employed to characterize the signals. Specifically, a novel, physiologically relevant peak matching algorithm is proposed and its performance is compared to features obtained from multi-resolution wavelet analysis. Once suitably characterized, the VEPs from different individuals are classified using a standard distance-measure based algorithm.