The Linear Relationship between Temporal Persistence, Number of Independent Features and Target EER

TL;DR

This paper establishes a linear relationship between the temporal persistence of features, the number of uncorrelated features, and target EER in biometric systems, aiding system planning.

Contribution

It introduces a model linking feature persistence, independence, and EER targets, providing practical guidance for biometric system design.

Findings

Linear relationships between persistence and feature count for various EERs

Use of synthetic features to validate the model

Guidelines for system planning based on persistence and feature independence

Abstract

If you have a target level of biometric performance (e.g. EER = 5% or 0.1%), how many units of unique information (uncorrelated features) are needed to achieve that target? We show, for normally distributed features, that the answer to that question depends on the temporal persistence of the feature set. We address these questions with synthetic features introduced in a prior report. We measure temporal persistence with an intraclass correlation coefficient (ICC). For 5 separate EER targets (5.0%, 2.0%, 1.0%, 0.5% and 0.1%) we provide linear relationships between the temporal persistence of the feature set and the log10(number of features). These linear relationships will help those in the planning stage, prior to setting up a new biometric system, determine the required temporal persistence and number of independent features needed to achieve certain EER targets.