TU Darmstadt / ULB / TUbiblio

Neighbor Distance Ratios and Dynamic Weighting in Multi-biometric Fusion

Damer, Naser and Alkhatib, Wael and Braun, Andreas and Kuijper, Arjan (2017):
Neighbor Distance Ratios and Dynamic Weighting in Multi-biometric Fusion.
pp. 491-500, IbPRIA 2017: 8th Iberian Conference on Pattern Recognition and Image Analysis, Faro, Portugal, June 20.-23., 2017, ISSN 0302-9743,
DOI: 10.1007/978-3-319-58838-4_54,
[Conference or Workshop Item]

Abstract

Multi-biometrics aims at building more accurate unified biometric decisions based on the information provided by multiple biometric sources. Information fusion is used to optimize the process of creating this unified decision. In previous works dealing with score-level multibiometric fusion, the scores of different biometric sources belonging to the comparison of interest are used to create the fused score. This is usually achieved by assigning static weights for the different biometric sources. In contrast, we focus on integrating the information imbedded in the relative relation between the comparison scores (within a 1:N comparison) in the biometric fusion process using a dynamic weighting scheme. This is performed by considering the neighbors distance ratio in the ranked comparisons to influence the dynamic weights of the fused scores. The evaluation was performed on the Biometric Scores Set BSSR1 database. The enhanced performance induced by including the neighbors distance ratio information within a dynamic weighting scheme in comparison to the baseline solution was shown by an average reduction of the equal error rate by more than 40% over the different test scenarios.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Damer, Naser and Alkhatib, Wael and Braun, Andreas and Kuijper, Arjan
Title: Neighbor Distance Ratios and Dynamic Weighting in Multi-biometric Fusion
Language: English
Abstract:

Multi-biometrics aims at building more accurate unified biometric decisions based on the information provided by multiple biometric sources. Information fusion is used to optimize the process of creating this unified decision. In previous works dealing with score-level multibiometric fusion, the scores of different biometric sources belonging to the comparison of interest are used to create the fused score. This is usually achieved by assigning static weights for the different biometric sources. In contrast, we focus on integrating the information imbedded in the relative relation between the comparison scores (within a 1:N comparison) in the biometric fusion process using a dynamic weighting scheme. This is performed by considering the neighbors distance ratio in the ranked comparisons to influence the dynamic weights of the fused scores. The evaluation was performed on the Biometric Scores Set BSSR1 database. The enhanced performance induced by including the neighbors distance ratio information within a dynamic weighting scheme in comparison to the baseline solution was shown by an average reduction of the equal error rate by more than 40% over the different test scenarios.

Uncontrolled Keywords: Multibiometrics, Verification, Biometric fusion, Biometric identification systems, CRISP
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: IbPRIA 2017: 8th Iberian Conference on Pattern Recognition and Image Analysis
Event Location: Faro, Portugal
Event Dates: June 20.-23., 2017
Date Deposited: 04 May 2020 12:43
DOI: 10.1007/978-3-319-58838-4_54
Official URL: https://link.springer.com/chapter/10.1007%2F978-3-319-58838-...
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details