Main menu
Home
Background
Call for participation
Databases
Reference systems
Scenarios
Access Control Scenario :
Mobile Scenario :
Final workshop
Participants
Search
Contact us
Background

The NoE BioSecure has been started in june 2004, in the domain of biometrics, grouping the critical mass of expertise required to promote Europe as a leading force in the field.

The main objective of this network is to strengthen and to integrate multidisciplinary research efforts in order to investigate biometrics-based identity authentication methods, for the purpose of meeting the trust and security requirements in our progressing digital information society. This goal will be attained through various integrating efforts. A common evaluation framework (such as databases, reference systems and assessment protocols) has been developed, participating to standardisation efforts.  

The first BioSecure Residential Workshop, August 2005, Paris

More than sixty doctoral, postdoctoral, senior and invited researchers met together for a duration of four weeks in August 2005, in Paris.

The objectives of this Residential workshop were to permit a common reliable evaluation of the existing biometric algorithms developed in the different laboratories involved in the network and in different modalities (hand, voice, face, talking faces, signature, multimodality) and to enable the integration of the research of the BioSecure partners. To this purpose, open-source reference systems were developed within the network enabling objective evaluation of the existing algorithms and fair comparison of the newly developed research prototypes. This goal was achieved by testing the reference systems and research prototypes on common integrated databases with related assessment protocols.

Objectives of BMEC 2007

The present evaluation campaign is a continuation of the work started during the Paris Residential Workshop. The objective is to pursue comparative evaluations of biometric algorithms.

However there are several main differences :

  • Tests will be performed on a large scale multimodal database acquired in 11 sites, under 3 different acquisition conditions corresponding to application oriented scenarios
  • Multimodality, at least score fusion strategies will be evaluated on a «true» multimodal database
  • Evaluation will be performed on «sequestered» data while the participants will have access to some development data in order to tune the parameters of their systems