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

M. Ali Akber Dewan, E. Granger, R. Sabourin, G. L. Marcialis, F. Roli

Research output: Chapter in Book/Report/Conference proceedingPublished Conference contributionpeer-review

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 change 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 reference stills images of each target individual (enrolled to the system) for robust spatiotemporal FR. Compared to the gallery-face-models produced by self-updating 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-face-models 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.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015
Pages196-202
Number of pages7
ISBN (Electronic)9781479975600
DOIs
Publication statusPublished - 2015
EventIEEE Symposium Series on Computational Intelligence, SSCI 2015 - Cape Town, South Africa
Duration: 8 Dec. 201510 Dec. 2015

Publication series

NameProceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015

Conference

ConferenceIEEE Symposium Series on Computational Intelligence, SSCI 2015
Country/TerritorySouth Africa
CityCape Town
Period8/12/1510/12/15

Fingerprint

Dive into the research topics of 'Video face recognition from a single still image using an adaptive appearance model tracker'. Together they form a unique fingerprint.

Cite this