Multi-task pose-invariant face recognition

Face images captured in unconstrained environments usually contain significant pose variation, which dramatically degrades the performance of algorithms designed to recognize frontal faces. This paper proposes a novel face identification framework capable of handling the full range of pose variation...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 24(2015), 3 vom: 15. März, Seite 980-93
1. Verfasser: Ding, Changxing (VerfasserIn)
Weitere Verfasser: Xu, Chang, Tao, Dacheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2015
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article Research Support, Non-U.S. Gov't