Show simple item record

dc.contributor.authorMeynet, Julien
dc.contributor.authorArsan, Taner
dc.contributor.authorMota, Javier Cruz
dc.contributor.authorThiran, Jean-Philippe Philippe H.
dc.date.accessioned2019-06-28T11:11:31Z
dc.date.available2019-06-28T11:11:31Z
dc.date.issued2008
dc.identifier.issn22195491
dc.identifier.urihttps://hdl.handle.net/20.500.12469/1613
dc.identifier.urihttps://ieeexplore.ieee.org/abstract/document/7080569
dc.description.abstractIn this paper a fast and an effective multi-view face tracking algorithm with head pose estimation is introduced. For modeling the face pose we employ a tree of boosted classifiers built using either Haar-like filters or Gauss filters. A first classifier extracts faces of any pose from the background. Then more specific classifiers discriminate between different poses. The tree of classifiers is trained by hierarchically sub-sampling the pose space. Finally Condensation algorithm is used for tracking the faces. Experiments show large improvements in terms of detection rate and processing speed compared to state-of-the-art algorithms.
dc.language.isoEnglish
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.titleFast multi-view face trackingwith pose estimation
dc.typeConference Paper
dc.relation.journalEuropean Signal Processing Conference
dc.contributor.khasauthorArsan, Taner


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record