Addressing missing values in kernel-based multimodal biometric fusion using neutral point substitution

Authors:
Norman Poh;David Windridge;Vadim Mottl;Alexander Tatarchuk;Andrey Eliseyev
Affiliations:
CVSSP, University of Surrey, Guildford, Surrey, UK;CVSSP, University of Surrey, Guildford, Surrey, UK;Computing Center of the Russian Academy of Sciences, Moscow, Russia;Computing Center of the Russian Academy of Sciences, Moscow, Russia;Computing Center of the Russian Academy of Sciences, Moscow, Russia
Venue:
IEEE Transactions on Information Forensics and Security
Year:
2010

Citing 10
Cited 2

On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Discriminative Bayesian Network Classifiers and Logistic Regression

Machine Learning
Handbook of Multibiometrics (International Series on Biometrics)

Handbook of Multibiometrics (International Series on Biometrics)
On fast supervised learning for normal mixture models with missing information

Pattern Recognition
A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms

Pattern Recognition
Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms

IEEE Transactions on Information Forensics and Security - Special issue on electronic voting
Score normalization in multimodal biometric systems

Pattern Recognition
The neutral point method for kernel-based combination of disjoint training data in multi-modal pattern recognition

MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB)

IEEE Transactions on Pattern Analysis and Machine Intelligence
How do correlation and variance of base-experts affect fusion in biometric authentication tasks?

IEEE Transactions on Signal Processing

A modified neutral point method for kernel-based fusion of pattern-recognition modalities with incomplete data sets

MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
A comparison of imputation methods for handling missing scores in biometric fusion

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In multimodal biometric information fusion, it is common to encounter missing modalities in which matching cannot be performed. As a result, at the match score level, this implies that scores will be missing. We address the multimodal fusion problem involving missing modalities (scores) using support vector machines (SVMs) with the neutral point substitution (NPS) method. The approach starts by processing each modality using a kernel. When a modality is missing, at the kernel level, the missing modality is substituted by one that is unbiased with regards to the classification, called a neutral point. Critically, unlike conventional missing-data substitution methods, explicit calculation of neutral points may be omitted by virtue of their implicit incorporation within the SVM training framework. Experiments based on the publicly available Biosecure DS2 multimodal (scores) data set show that the SVM-NPS approach achieves very good generalization performance compared to the sum rule fusion, especially with severe missing modalities.