FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

Video face recognition from a single still image using an adaptive appearance model tracker

Downloads

Downloads per month over past year

Dewan, M. Ali Akber and Granger, E. and Sabourin, R. and Marcialis, G. L. and Roli, F.. 2015. « Video face recognition from a single still image using an adaptive appearance model tracker ». In 2015 IEEE Symposium Series on Computational Intelligence (Cape Town, South Africa, Dec. 7-10, 2015), pp. 196-202. IEEE.

[img]
Preview
PDF
Video-face-recognition-from-a-single-still-image-using-an-adaptive-appearance-model-tracker.pdf

Download (624kB) | Preview

Abstract

Systems for still-to-video face recognition (FR) are typically used to detect target individuals in watch-list screening applications. These surveillance applications are challenging because the appearance of faces changes according to capture conditions, and very few reference stills are available a priori for enrollment. To improve performance, an adaptive appearance model tracker (AAMT) is proposed for on-line learning of a track-face-model linked to each individual appearing in the scene. Meanwhile, these models are matched over successive frames against stored gallery-face-models, extracted from reference still images of each target individual (enrolled to the system) for robust spatiotemporal FR. In addition, compared to the gallery-face-models produced by selfupdating FR systems, the track-face-models (produced by the AAMT-FR system) are updated from facial captures that are more reliably selected, and can incorporate greater intra-class variations from the operational environment. Track-facemodels allow selecting facial captures for modeling more reliably than self-updating FR systems, and can incorporate a greater diversity of intra-class variation from the operational environment. Performance of the proposed approach is compared with several state-of-the-art FR systems on videos from the Chokepoint dataset when a single reference template per target individual is stored in the gallery. Experimental results show that the proposed system can achieve a significantly higher level of FR performance, especially when the diverse facial appearances captured through AAMT correspond to that of reference stills.

Item Type: Conference proceeding
Professor:
Professor
Granger, Éric
Sabourin, Robert
Affiliation: Génie de la production automatisée, Génie de la production automatisée
Date Deposited: 03 Feb 2016 20:36
Last Modified: 22 Aug 2018 20:18
URI: http://espace2.etsmtl.ca/id/eprint/12258

Actions (login required)

View Item View Item