The one-to-many multi-modal fusion challenge

The One-to-many Multi-modal Fusion Challenge is presented, with the aim of promoting academic research into one-to-many methods of fusion for large-scale biometric systems. Although most research into fusion has been conducted using verification (one-to-one) comparison results, there is greater demand among government agencies for one-to-many fusion. The fusion challenge makes commercial iris and face matching results available to the public. Results are computed over operational data. Specific challenges that are relevant to deployers of biometric systems are put forth, and an adaptation of Neyman-Pearson fusion is used to compute baseline results for some of the challenges. The results show that there is potential to improve recognition accuracy by fusing comparison results from multiple iris algorithms, even when one of the algorithms is considerably more accuracy than the other.