Ageing Drift in Binary Face Templates: A Bits-per-Decade Analysis

TL;DR

This study analyzes how binary face templates degrade over time in terms of bits per decade, revealing that shorter codes are more stable and discussing implications for biometric deployment and maintenance.

Contribution

It introduces a method to quantify face template ageing directly in bits per decade and compares stability across different code lengths using a large longitudinal dataset.

Findings

Median drift of 1.357 bits/decade for 64-bit templates

Median drift of 2.571 bits/decade for 128-bit templates

Shorter codes are more age-stable at a fixed decision threshold

Abstract

We study the longitudinal stability of compact binary face templates and quantify ageing drift directly in bits per decade. Float embeddings from a modern face CNN are compressed with PCA-ITQ into 64- and 128-bit codes. For each identity in AgeDB with at least three distinct ages, we form all genuine pairs and fit a per-identity linear model of Hamming distance versus absolute age gap. Across 566 identities, the median slope is 1.357 bits per decade for 64-bit templates and 2.571 bits per decade for 128-bit templates, with tight non-parametric 95 percent bootstrap confidence intervals. The distributions are predominantly positive, indicating a small but systematic increase in intra-class distance over time. Because drift scales with code length, shorter codes are inherently more age-stable at a fixed decision threshold. We connect these slopes to operating characteristics by reporting EER and TPR at FAR = 1 percent in three age bins. We discuss implications for smart-card and match-on-card deployments, including simple mitigations such as periodic re-enrolment and targeted parity on empirically unstable bit positions. Code and CSV artifacts are provided to support reproducibility.