Temporal Persistence and Intercorrelation of Embeddings Learned by an End-to-End Deep Learning Eye Movement-driven Biometrics Pipeline

TL;DR

This study investigates how temporal persistence and intercorrelation of eye movement embeddings relate to biometric performance in a deep learning system, confirming that persistence predicts success and embeddings are weakly intercorrelated.

Contribution

It demonstrates that temporal persistence is a key predictor of biometric accuracy and that deep learning embeddings are generally weakly intercorrelated, extending prior findings to modern DL systems.

Findings

Temporal persistence predicts biometric performance.

Deep learning embeddings are weakly intercorrelated.

Data quality influences biometric accuracy.

Abstract

What qualities make a feature useful for biometric performance? In prior research, pre-dating the advent of deep learning (DL) approaches to biometric analysis, a strong relationship between temporal persistence, as indexed by the intraclass correlation coefficient (ICC), and biometric performance (Equal Error Rate, EER) was noted. More generally, the claim was made that good biometric performance resulted from a relatively large set of weakly intercorrelated features with high ICC. The present study aimed to determine whether the same relationships are found in a state-of-the-art DL-based eye movement biometric system (``Eye-Know-You-Too''), as applied to two publicly available eye movement datasets. To this end, we manipulate various aspects of eye-tracking signal quality, which produces variation in biometric performance, and relate that performance to the temporal persistence and intercorrelation of the resulting embeddings. Data quality indices were related to EER with either linear or logarithmic fits, and the resulting model R^2 was noted. As a general matter, we found that temporal persistence was an important predictor of DL-based biometric performance, and also that DL-learned embeddings were generally weakly intercorrelated.