A new protocol for multi-biometric systems evaluation maintaining the dependencies between biometric scores

We address the problem of measuring the dependency of multibiometric systems scores, using KolmogorovSmirnov and Mutual Information criteria, and studying the validity of performance evaluation on chimeric persons. On the NIST-BSSR1 database, we formalize a common assumption in the literature: for independent scores, multibiometric systems can be evaluated on random chimeric persons. We show that this is not valid for dependent scores and propose a novel protocol for building cluster-based chimeric persons maintaining the level of dependency between scores. Finally, we show that performance evaluation for dependent modalities on such persons is equivalent to that obtained on real persons.