To Impute or Not: Recommendations for Multibiometric Fusion
This work addresses performance degradation in biometric recognition systems due to missing data, offering practical recommendations for researchers and practitioners, though it is incremental in nature.
The paper tackled the problem of missing scores in multibiometric fusion, evaluating various imputation approaches on three datasets and finding that imputation improves accuracy, class balancing mitigates biases, and multivariate or univariate methods are beneficial depending on score correlations.
Combining match scores from different biometric systems via fusion is a well-established approach to improving recognition accuracy. However, missing scores can degrade performance as well as limit the possible fusion techniques that can be applied. Imputation is a promising technique in multibiometric systems for replacing missing data. In this paper, we evaluate various score imputation approaches on three multimodal biometric score datasets, viz. NIST BSSR1, BIOCOP2008, and MIT LL Trimodal, and investigate the factors which might influence the effectiveness of imputation. Our studies reveal three key observations: (1) Imputation is preferable over not imputing missing scores, even when the fusion rule does not require complete score data. (2) Balancing the classes in the training data is crucial to mitigate negative biases in the imputation technique towards the under-represented class, even if it involves dropping a substantial number of score vectors. (3) Multivariate imputation approaches seem to be beneficial when scores between modalities are correlated, while univariate approaches seem to benefit scenarios where scores between modalities are less correlated.