Abstract-Although still-to-video face recognition is an important function in watchlist screening, state-of-the-art systems often yield limited performance due to camera inter-operability and to variations in capture conditions. Therefore, the visual comparison of faces captured in unconstrained low-quality videos against a matching high-quality reference facial still image captured under controlled conditions is required in many surveillance applications to limit the number of costly false matches. To improve the visual appearance of faces captured in videos, this paper presents a new super-resolution (SR) pipeline that is suitable for fast adjudication of face-matches produced by an automated system. In this pipeline, face quality measures are used to rank and select face captures belonging to a facial trajectory, and multi-image SR iteratively enhances the appearance of a super-resolved face image. Face selection is optimized and registered using graphical models. Experiments with the Chokepoint dataset show that the proposed pipeline efficiently produces super-resolved face images by ranking best quality ROIs in a trajectory. To select the best face captures for SR, this pipeline exploits a strong correlation existing between pose and sharpness quality measurements.

Approaches to calculating upper-bound estimates of recognition probability are proposed that can be used for a more general class of models. One of estimates determines the stability of object coverage by classification algorithms on the basis of distribution of distances between objects, and another estimate is underlain by leave-one-out cross-validation. This considerably simplifies and facilitates the construction of estimates.

No abstract