Databases

Four different databases (DB1, DB2, DB3 and DB4) were collected by using the following sensors/technologies:

• DB1: optical sensor "V300" by CrossMatch
• DB2: optical sensor "U.are.U 4000" by Digital Persona
• DB3: thermal sweeping sensor "FingerChip FCD4B14CB" by Atmel
• DB4: synthetic fingerprint generation

NOTE: FVC2004 databases are markedly more difficult than FVC2002 and FVC2000 ones, due to the perturbations deliberately introduced (see below). Therefore one should neither compare error rates among different FVC competitions, nor conclude that the state-of-the art in fingerprint matching is not improving.

Students (24 years old on the average) enrolled in the Computer Science degree program at the University of Bologna kindly agreed to act as volunteers for providing fingerprints:

• volunteers were randomly partitioned into three groups of 30 persons; each group was associated to a DB and therefore to a different fingerprint scanner (different subjects in each database, except for a small overlap of five volunteers present in two databases);
• each volunteer was invited to present him/herself at the collection place in three distinct sessions, with at least two weeks time separating each session;
• forefinger and middle finger of both the hands (four fingers total) of each volun-teer were acquired by interleaving the acquisition of the different fingers to maxi-mize differences in finger placement;
• no efforts were made to control image quality and the sensor platens were not systematically cleaned;
• at each session, four impressions were acquired of each of the four fingers of each volunteer;
• during the first sessions, individuals were asked to put the finger at a slightly different vertical position (in impressions 1 and 2) and to alternate low and high pressure against the sensor surface (impressions 3 and 4);
• during the second session, individuals were requested to exaggerate skin distortion (impressions 1 and 2) and rotation (3 and 4) of the finger;
• during the third session, fingers were dried (impressions 1 and 2) and moistened (3 and 4).

At the end of the data collection, for each database a total of 120 fingers and 12 impressions per finger (1440 impressions) were gathered. As in previous editions, the size of each database to be used in the test was established as 110 fingers wide (w) and 8 impressions per finger deep (d) (880 fingerprints in all); collecting some additional data gave a margin in case of collection/labeling errors.

Fingers from 101 to 110 (set B) have been made available to the participants to allow parameter tuning before the submission of the algorithms; the benchmark is then constituted by fingers numbered from 1 to 100 (set A).

The following figure shows a sample image from each database:

A minimal training of the volunteers has been performed before the first acquisition session and failure to acquire has been measured during the three sessions, counting the number of attempts required to acquire a valid sample (see following table).