(Created page with " == Abstract == hough still-to-video face recognition is an important function in watchlist screening, state-of-the-art systems often yield limited performance due to camera...") |
m (Scipediacontent moved page Draft Content 925068725 to Bordallo et al 2016a) |
(No difference)
| |
Latest revision as of 17:34, 3 February 2021
Abstract
hough 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.
Original document
The different versions of the original document can be found in:
Document information
Published on 01/01/2016
Volume 2016, 2016
DOI: 10.1109/ipta.2015.7367145
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?