Longitudinal Study of Facial Biometrics at the BEZ: Temporal Variance Analysis

TL;DR

This longitudinal study analyzes facial biometric data over two and a half years, revealing significant daily fluctuations in recognition scores and emphasizing the importance of long-term testing for biometric reliability.

Contribution

It provides the first extensive long-term analysis of facial biometric variability across diverse populations in a controlled environment.

Findings

Recognition scores fluctuate more daily than over years

Long-term biometric stability varies among individuals

Highlights need for extended testing in biometric systems

Abstract

This study presents findings from long-term biometric evaluations conducted at the Biometric Evaluation Center (bez). Over the course of two and a half years, our ongoing research with over 400 participants representing diverse ethnicities, genders, and age groups were regularly assessed using a variety of biometric tools and techniques at the controlled testing facilities. Our findings are based on the General Data Protection Regulation-compliant local bez database with more than 238.000 biometric data sets categorized into multiple biometric modalities such as face and finger. We used state-of-the-art face recognition algorithms to analyze long-term comparison scores. Our results show that these scores fluctuate more significantly between individual days than over the entire measurement period. These findings highlight the importance of testing biometric characteristics of the same individuals over a longer period of time in a controlled measurement environment and lays the groundwork for future advancements in biometric data analysis.