Multi-spectral Imaging for Robust Ocular Biometrics

Abstract

Recent development of sensors has allowed to explore the possibility of biometric authentication beyond visible spectrum.Particularly, multi-spectral imaging has shown a great potential in biometrics to work robustly under unknown varying illumination conditions for face recognition. While face biometrics in traditional settings has also indicated the applicability of ocular regions for improving the recognition performance, there are not many works that have explored recent imaging techniques. In this paper, we present a study that explores the possibility of recognizing ocular biometric features using multi-spectral imaging. While exploring the possibility of recognizing the periocular region in different spectral bands, this work also presents the performance variation of periocular region for cross-spectral recognition. We have captured a new ocular image database in eight narrow spectral bands across Visible (VIS) and Near-Infra-Red (NIR) spectrum (530nm to 1000nm) using our custom built sensor. The database consists of images from 52 subjects with a sample size of 4160 spectral band images captured in two different sessions. The extensive set of experimental evaluation obtained on the state-of-the-art methods indicate highest recognition rate of 96.92% at Rank-1, demonstrating the potential of multi-spectral imaging for robust periocular recognition.