Performance evaluation is important for all biometric modalities and particularly so for fingerprint recognition, which is receiving widespread attention for citizen identity verification and identification in large-scale applications. Unambiguously and reliably assessing the performance of current fingerprint recognition technology is mandatory for understanding its limitations and addressing future research. After the success of the first four fingerprint verification competitions (FVC2000 [1], FVC2002 [2], FVC2004 [3] and FVC2006 [4]), the Biometric System Laboratory (University of Bologna) has decided to organize a new online evaluation campaign for fingerprint recognition technologies: FVC-onGoing. FVC-onGoing offers web-based automatic evaluation of fingerprint recognition algorithms on a set of sequestered datasets, reporting results using well known performance indicators and metrics. The aim is to track the advances in fingerprint recognition technologies, through continuously updated independent testing and reporting of performances on given benchmarks. The benchmark datasets will not evolve over time; in case new datasets will be added in the future, they will form a different benchmark or a new version of an existing one: in this way, only results obtained on the same data will be compared. The algorithms will be evaluated using strongly supervised approaches (see [3]), to maximize trustworthiness of the results.
FVC-onGoing: On-line Evaluation of Fingerprint Recognition Algorithms / R. Cappelli; D. Maltoni. - ELETTRONICO. - (2010), pp. 1-4. (Intervento presentato al convegno International Biometric Performance Conference tenutosi a GAITHERSBURG nel March 1-5, 201).
FVC-onGoing: On-line Evaluation of Fingerprint Recognition Algorithms
CAPPELLI, RAFFAELE;MALTONI, DAVIDE
2010
Abstract
Performance evaluation is important for all biometric modalities and particularly so for fingerprint recognition, which is receiving widespread attention for citizen identity verification and identification in large-scale applications. Unambiguously and reliably assessing the performance of current fingerprint recognition technology is mandatory for understanding its limitations and addressing future research. After the success of the first four fingerprint verification competitions (FVC2000 [1], FVC2002 [2], FVC2004 [3] and FVC2006 [4]), the Biometric System Laboratory (University of Bologna) has decided to organize a new online evaluation campaign for fingerprint recognition technologies: FVC-onGoing. FVC-onGoing offers web-based automatic evaluation of fingerprint recognition algorithms on a set of sequestered datasets, reporting results using well known performance indicators and metrics. The aim is to track the advances in fingerprint recognition technologies, through continuously updated independent testing and reporting of performances on given benchmarks. The benchmark datasets will not evolve over time; in case new datasets will be added in the future, they will form a different benchmark or a new version of an existing one: in this way, only results obtained on the same data will be compared. The algorithms will be evaluated using strongly supervised approaches (see [3]), to maximize trustworthiness of the results.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.