An adaptive multi-biometric incremental fusion strategy in the context of BMEC 2007

We present the general principles of a dynamical sequential fusion strategy for multibiometric systems allowing reducing the cost associated to the use of different modalities while preserving a good performance compared to that of a global fusion system. We have implemented this strategy in the BME...

Full description

Saved in:
Bibliographic Details
Published in2008 10th International Conference on Control Automation Robotics and Vision pp. 1144 - 1149
Main Authors Allano, L., Garcia-Salicetti, S., Dorizzi, B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2008
Subjects
Access control
Automatic control
Biometrics
Control systems
Cost function
cost optimization
evaluation
fusion
incremental fusion
missing values
Multi-biometrics
Robot control
Robot vision systems
Robotics and automation
Robustness
Telecommunication control
Online AccessGet full text

Cover

More Information
Summary:We present the general principles of a dynamical sequential fusion strategy for multibiometric systems allowing reducing the cost associated to the use of different modalities while preserving a good performance compared to that of a global fusion system. We have implemented this strategy in the BMEC (BioSecure multimodal evaluation campaign) 2007 cost-sensitive evaluation. We show that this approach was very robust to the occurrence of missing data thanks to its adaptive implementation.
ISBN:9781424422869
1424422868
DOI:10.1109/ICARCV.2008.4795682