Bi-Encoder Contrastive Learning for Fingerprint and Iris Biometrics

TL;DR

This paper investigates the correlation between different biometric modalities using Bi-Encoder contrastive learning, demonstrating that iris and fingerprint biometrics are not statistically independent, with new application of Vision Transformers for biometric matching.

Contribution

First application of Vision Transformers in biometric matching, challenging the assumption of independence among biometric traits, and providing empirical evidence of correlations within iris and fingerprint data.

Findings

Iris-to-iris matching achieves 91 ROC AUC.

Fingerprint models confirm intra-subject correlation.

Cross-modal matching performance is only slightly above chance.

Abstract

There has been a historic assumption that the biometrics of an individual are statistically uncorrelated. We test this assumption by training Bi-Encoder networks on three verification tasks, including fingerprint-to-fingerprint matching, iris-to-iris matching, and cross-modal fingerprint-to-iris matching using 274 subjects with $\sim$100k fingerprints and 7k iris images. We trained ResNet-50 and Vision Transformer backbones in Bi-Encoder architectures such that the contrastive loss between images sampled from the same individual is minimized. The iris ResNet architecture reaches 91 ROC AUC score for iris-to-iris matching, providing clear evidence that the left and right irises of an individual are correlated. Fingerprint models reproduce the positive intra-subject suggested by prior work in this space. This is the first work attempting to use Vision Transformers for this matching. Cross-modal matching rises only slightly above chance, which suggests that more data and a more sophisticated pipeline is needed to obtain compelling results. These findings continue challenge independence assumptions of biometrics and we plan to extend this work to other biometrics in the future. Code available: https://github.com/MatthewSo/bio_fingerprints_iris.