TY  - JOUR
ID  - ortega10:tpami
T1  - The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB)
A1  - Ortega-Garcia, Javier
A1  - Fierrez, Julian
A1  - Alonso-Fernandez, Fernando
A1  - Galbally, Javier
A1  - Freire, Manuel R.
A1  - Gonzalez-Rodriguez, Joaquin
A1  - Garcia-Mateo, Carmen
A1  - Alba-Castro, Jose-Luis
A1  - Gonzalez-Agulla, Elisardo
A1  - Otero-Muras, Enrique
A1  - Garcia-Salicetti, Sonia
A1  - Allano, Lorene
A1  - Ly-Van, Bao
A1  - Dorizzi, Bernadette
A1  - Kittler, Josef
A1  - Bourlai, Thirimachos
A1  - Poh, Norman
A1  - Deravi, Farzin
A1  - Ng, Ming W. R.
A1  - Fairhurst, Michael
A1  - Hennebert, Jean
A1  - Humm, Andreas
A1  - Tistarelli, Massimo
A1  - Brodo, Linda
A1  - Richiardi, Jonas
A1  - Drygajlo, Andrzej
A1  - Ganster, Harald
A1  - Sukno, Federico M.
A1  - Pavani, Sri-Kaushik
A1  - Frangi, Alejandro
A1  - Akarun, Lale
A1  - Savran, Arman
JA  - IEEE Transactions on Pattern Analysis and Machine Intelligence
Y1  - 2010
VL  - 32
SP  - 1097
EP  - 1111
PB  - IEEE Computer Society
AD  - Los Alamitos, CA, USA
SN  - 0162-8828
M2  - doi: 10.1109/tpami.2009.76
KW  - Benchmarking
KW  - Biometrics
KW  - machine learning
N2  - A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence (NoE) is presented. It comprises more than 600 individuals acquired simultaneously in three scenarios: i) over the Internet, ii) in an office environment with desktop PC, and iii) in indoor/outdoor environments with mobile portable hardware. Data has been acquired over two acquisition sessions and using different sensors in certain modalities. The three scenarios include a common part of audio and video data (face still images and talking face videos). Also, signature and fingerprint data has been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data was acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions taking part in the BioSecure NoE. Additional features of the BioSecure Multimodal Database (BMDB) are: balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity (language, face, etc.), availability of demographic data (age, gender, handedness, visual aids, manual worker and English proficiency) and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB database allow to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation Campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.
ER  -