Can Facial Uniqueness be Inferred from Impostor Scores?

TL;DR

This paper investigates the reliability of facial uniqueness measures derived from impostor scores, revealing their high sensitivity to image quality variations such as pose, noise, and blur, and demonstrating instability in existing measures.

Contribution

The study highlights the instability of impostor-based facial uniqueness measures under varying image quality conditions and evaluates a recent proposed measure's robustness.

Findings

Impostor scores are highly unstable with image quality variations.

Existing impostor-based measures can be unreliable in poor quality images.

The instability affects the reliability of facial uniqueness assessments.

Abstract

In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores. In this paper, we show that such uniqueness measures are highly unstable in the presence of image quality variations like pose, noise and blur. We also experimentally demonstrate the instability of a recently introduced impostor-based uniqueness measure of [Klare and Jain 2013] when subject to poor quality facial images.