How Unique Is a Face: An Investigative Study

TL;DR

This study investigates the factors influencing the uniqueness of faces as biometric identifiers, analyzing how image quality, demographic variables, and dataset characteristics affect face recognition performance.

Contribution

It provides experimental insights into how various factors impact face biometric uniqueness, highlighting the need for a deeper understanding of this concept.

Findings

Factors like image resolution and dataset size significantly affect face uniqueness.

Different feature extraction algorithms show varying sensitivity to demographic factors.

Results suggest the importance of considering these factors in face recognition system design.

Abstract

Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector. Surprisingly, while widely accepted, we still lack the understanding of uniqueness or distinctiveness of faces as biometric modality. In this work, we study the impact of factors such as image resolution, feature representation, database size, age and gender on uniqueness denoted by the Kullback-Leibler divergence between genuine and impostor distributions. Towards understanding the impact, we present experimental results on the datasets AT&T, LFW, IMDb-Face, as well as ND-TWINS, with the feature extraction algorithms VGGFace, VGG16, ResNet50, InceptionV3, MobileNet and DenseNet121, that reveal the quantitative impact of the named factors. While these are early results, our findings indicate the need for a better understanding of the concept of biometric uniqueness and its implication on face recognition.