Background

The first international competition on fingerprint verification (FVC2000) was organized in 2000. This event received a great attention both from academic and industrial biometric communities. While on the one hand, it established a common benchmark allowing developers to unambiguously compare their algorithms, on the other hand it provided an overview of the state-of-the-art in fingerprint recognition. FVC2000 was undoubtedly a successful initiative as evident by the following:

• 11 organizations participated in the contest
• 4 different fingerprint databases were collected
• The results were presented at ICPR 2000 (International Conference on Pattern Recognition), Barcelona, September 2000.
• A detailed technical report was prepared and made available on the web. The report presents motivation, protocol, database collection, experiments and results of FVC2000.
• A CD ROM containing the four fingerprint databases and the report was prepared and more than 70 copies have been purchased by major institutions and companies working in biometrics.
• A web site has been created and maintained (http://bias.csr.unibo.it/fvc2000); this web site has been visited more than 11,000 times since September 14, 2000.
• A paper on FVC2000 has been accepted for publication in an upcoming issue of the IEEE Transaction on Pattern Analysis Machine Intelligence (PAMI).
• Several scientific groups are currently using FVC2000 databases in their experiments.
• Some companies which initially did not participate to the competition have requested us to certify their performance and to be added to the web site.

The interest aroused by FVC2000 and the encouragements received, induced the organizers to schedule a new competition for 2002.

Aim

The continuous advances in the biometric system field and, in particular, in fingerprint techniques (both for recognition approaches and sensing devices), quickly make the performance evaluation initiatives obsolete.
The aim of this competition is to track recent advances in fingerprint verification, for both academia and industry, and to provide up to date state-of-the-art in fingerprint technology.
This competition should not be conceived as an official performance certification of biometric systems, since:

• the databases used in this contest have not been necessarily acquired in a real environment and according to a formal protocol.
• only parts of the system software will be evaluated by using images from sensors not native to each system.

In any event, the results obtained will give a useful overview of the state-of-the-art in this field and will provide guidance to the participants for improving their algorithms.