A major sustained objective of the BioSecure Network of excellence has been to build a common evaluation framework designed to facilitate reliable benchmarking and comparable evaluation of biometrics-based research developments. The credibility of such a framework is directly linked to the quality of its components, amongst which the database is probably the most crucial. Further to initial work made with existing material, BioSecure has to consider the design, collection and distribution of a complete new multimodal database, answering the required needs and representing a major effort of integration.
The BioSecure database has been designed to include data corresponding to face, voice, iris, fingerprint, hand and signature modalities, within the framework of three datasets corresponding to real multimodal, multi-session and multi-environment situations. Moreover, to increase the representativeness of the database, BioSecure participants agreed to collect the above mentioned data in a variety of sites (11 at the end) involving a number of countries spread over Europe. Not all the centers contributed to the acquisition of the three datasets. Nevertheless, each acquisition center completed for about 100 individuals the acquisition of the whole set of data (two sessions per person) for the datasets they were in charge.
The three datasets which compose the BioSecure multimodal database are:
The PowerPoint presentation of the BioSecure multimodal database can be downloaded here.
According to the terms of a joint ownership and licence agreement signed between the acquisition centers and the BioSecure Association, this Association has the right to handle on an exclusive basis the distribution of the data collected during the BioSecure project. Such an arrangement allow an easy access to authenticated BioSecure material.