Multispectral Biometrics System Framework: Application to Presentation Attack Detection

TL;DR

This paper introduces a multispectral biometric system framework that captures data across visible to infrared spectra, enabling rapid presentation attack detection through deep learning analysis of diverse spectral data.

Contribution

It presents the first unified multispectral biometric system framework utilizing diverse electromagnetic spectrum bands for presentation attack detection.

Findings

Deep learning effectively distinguishes live from fake samples across spectral bands.

Different spectral bands have varying strengths in presentation attack detection.

The system captures large data volumes quickly for comprehensive analysis.

Abstract

In this work, we present a general framework for building a biometrics system capable of capturing multispectral data from a series of sensors synchronized with active illumination sources. The framework unifies the system design for different biometric modalities and its realization on face, finger and iris data is described in detail. To the best of our knowledge, the presented design is the first to employ such a diverse set of electromagnetic spectrum bands, ranging from visible to long-wave-infrared wavelengths, and is capable of acquiring large volumes of data in seconds. Having performed a series of data collections, we run a comprehensive analysis on the captured data using a deep-learning classifier for presentation attack detection. Our study follows a data-centric approach attempting to highlight the strengths and weaknesses of each spectral band at distinguishing live from fake samples.