A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals
IEEE Transactions on Pattern Analysis and Machine Intelligence
The nature of statistical learning theory
The nature of statistical learning theory
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Recent Advances in Speaker Recognition (Invited Paper)
AVBPA '97 Proceedings of the First International Conference on Audio- and Video-Based Biometric Person Authentication
Information fusion in biometrics
Pattern Recognition Letters - Special issue: Audio- and video-based biometric person authentication (AVBPA 2001)
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Combining Pattern Classifiers: Methods and Algorithms
Combining Pattern Classifiers: Methods and Algorithms
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Score normalization in multimodal biometric systems
Pattern Recognition
Fuzzy fusion in multimodal biometric systems
KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part I
An introduction to biometric recognition
IEEE Transactions on Circuits and Systems for Video Technology
How to handle missing data in robust multi-biometrics verification
International Journal of Biometrics
| Hi-index | 0.00 |
In multimodal biometric authentication, the unimodal scores are used to produce the final decision, following the score fusion approach. Researchers have often decomposed the score fusion problem into two steps: a 'score normalisation' and a 'fusion' step. This paper shows the fusion studies and experiments carried out by the authors. A special effort has been made to manipulate unimodal scores prior to their fusion. We propose a score normalisation technique consisting of a bilinear transformation applied to the independent scores, so that the unimodal thresholds become uniform and the data closest to these thresholds have greater separation between them. Our results show that this procedure improves the final results when compared with classic normalisation procedures. Several score fusion strategies were used in the experiments. All the experiments were carried out using the same scores, that have been obtained through the processing of three unimodal verification systems on three independent biometrical databases.