PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms
Norman Poh, T Bourlai and Josef Kittler
Pattern Recognition Volume 43, Number 3, pp. 1094-1105, 2010.

Abstract

This paper presents a testbed, called the Biosecure DS2s core-and-quality database, forevaluating, comparing and benchmarking score-level fusion algorithms for multimodal biometric authentication. It is designed to benchmark quality-dependent, client-specific, cost-sensitive fusion algorithms. A quality- dependent fusion algorithm is one which attempts to devise a fusion strategy that is dependent on the biometric sample quality. A client-specific fusionalgorithm, on the other hand, exploits the specific score characteristics of each enrolled user in order to customize the fusion strategy. Finally, a cost- sensitive fusion algorithm attempts to select a subset of biometric modalities/systems (at a specified cost) in order to obtain the maximal generalization performance. To the best of our knowledge, the BioSecure DS2 dataset is the first one designed to benchmark the above three aspects of fusion algorithms. This paper contains some base line experimental results for evaluating the above three types of fusion scenarios.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Multimodal Integration
ID Code:6834
Deposited By:Teo de Campos
Deposited On:08 March 2010