Person Identification Using Temporal Analysis of Facial Blood Flow

Abstract

Biometrics play an important role in modern access control and security systems. The need of novel biometrics to complement traditional biometrics has been at the forefront of research. The Facial Blood Flow (FBF) biometric trait, recently proposed by our team, is a spatio-temporal representation of facial blood flow, constructed using motion magnification from facial areas where skin is visible. Due to its design and construction, the FBF does not need information from the eyes, nose, or mouth, and, therefore, it yields a versatile biometric of great potential. In this work, we evaluate the effectiveness of novel temporal partitioning and Fast Fourier Transform-based features that capture the temporal evolution of facial blood flow. These new features, along with a “time-distributed” Convolutional Neural Network-based deep learning architecture, are experimentally shown to increase the performance of FBF-based person identification compared to our previous efforts. This study provides further evidence of FBF’s potential for use in biometric identification.