LocalScore: Local Density-Aware Similarity Scoring for Biometrics

TL;DR

LocalScore is a density-aware scoring method for open-set biometrics that improves detection of non-enrolled subjects by leveraging local feature distribution, leading to significant performance gains across multiple modalities.

Contribution

It introduces LocalScore, a novel, architecture-agnostic scoring algorithm that incorporates local density information to enhance open-set biometric performance.

Findings

FNIR@FPIR reduced from 53% to 40%

TAR@FAR improved from 51% to 74%

Effective across multiple biometric modalities

Abstract

Open-set biometrics faces challenges with probe subjects who may not be enrolled in the gallery, as traditional biometric systems struggle to detect these non-mated probes. Despite the growing prevalence of multi-sample galleries in real-world deployments, most existing methods collapse intra-subject variability into a single global representation, leading to suboptimal decision boundaries and poor open-set robustness. To address this issue, we propose LocalScore, a simple yet effective scoring algorithm that explicitly incorporates the local density of the gallery feature distribution using the k-th nearest neighbors. LocalScore is architecture-agnostic, loss-independent, and incurs negligible computational overhead, making it a plug-and-play solution for existing biometric systems. Extensive experiments across multiple modalities demonstrate that LocalScore consistently achieves substantial gains in open-set retrieval (FNIR@FPIR reduced from 53% to 40%) and verification (TAR@FAR improved from 51% to 74%). We further provide theoretical analysis and empirical validation explaining when and why the method achieves the most significant gains based on dataset characteristics.