On Missing Scores in Evolving Multibiometric Systems

TL;DR

This paper investigates the challenge of missing scores in evolving multibiometric systems and demonstrates that score imputation combined with simple fusion methods significantly improves recognition accuracy even with up to 90% missing data.

Contribution

It introduces a comprehensive study of missing score impact on both verification and identification, proposing effective imputation methods, especially iterative KNN, for improved fusion performance.

Findings

Score imputation with sum fusion enhances accuracy with high missing data.

Iterative KNN imputation outperforms other methods across tasks.

Fusion after imputation consistently surpasses no-imputation approaches.

Abstract

The use of multiple modalities (e.g., face and fingerprint) or multiple algorithms (e.g., three face comparators) has shown to improve the recognition accuracy of an operational biometric system. Over time a biometric system may evolve to add new modalities, retire old modalities, or be merged with other biometric systems. This can lead to scenarios where there are missing scores corresponding to the input probe set. Previous work on this topic has focused on either the verification or identification tasks, but not both. Further, the proportion of missing data considered has been less than 50%. In this work, we study the impact of missing score data for both the verification and identification tasks. We show that the application of various score imputation methods along with simple sum fusion can improve recognition accuracy, even when the proportion of missing scores increases to 90%. Experiments show that fusion after score imputation outperforms fusion with no imputation. Specifically, iterative imputation with K nearest neighbors consistently surpasses other imputation methods in both the verification and identification tasks, regardless of the amount of scores missing, and provides imputed values that are consistent with the ground truth complete dataset.