Identifying the Origin of Finger Vein Samples Using Texture Descriptors

TL;DR

This paper demonstrates that texture descriptors combined with SVM classification can effectively identify the sensor origin of finger vein images, offering a promising alternative to PRNU-based methods in biometric systems.

Contribution

It introduces a texture classification approach for finger vein sensor identification, outperforming PRNU-based methods in certain scenarios.

Findings

High accuracy in sensor model identification using texture descriptors

Effective on both raw and ROI finger vein samples

Texture descriptors are competitive with PRNU methods

Abstract

Identifying the origin of a sample image in biometric systems can be beneficial for data authentication in case of attacks against the system and for initiating sensor-specific processing pipelines in sensor-heterogeneous environments. Motivated by shortcomings of the photo response non-uniformity (PRNU) based method in the biometric context, we use a texture classification approach to detect the origin of finger vein sample images. Based on eight publicly available finger vein datasets and applying eight classical yet simple texture descriptors and SVM classification, we demonstrate excellent sensor model identification results for raw finger vein samples as well as for the more challenging region of interest data. The observed results establish texture descriptors as effective competitors to PRNU in finger vein sensor model identification.