KIT | KIT-Bibliothek | Impressum | Datenschutz
Open Access Logo
URN: urn:nbn:de:swb:90-404258

Discriminative Appearance Models for Face Alignment

Gao, Hua

The proposed face alignment algorithm uses local gradient features as the appearance representation. These features are obtained by pixel value comparison, which provide robustness against changes in illumination, as well as partial occlusion and local deformation due to the locality. The adopted features are modeled in three discriminative methods, which correspond to different alignment cost functions. The discriminative appearance modeling alleviate the generalization problem to some extent.

Zugehörige Institution(en) am KIT Institut für Anthropomatik (IFA)
Publikationstyp Hochschulschrift
Jahr 2013
Sprache Englisch
Identifikator KITopen-ID: 1000040425
Verlag Karlsruhe
Abschlussart Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik (IFA)
Prüfungsdaten 19.06.2013
Referent/Betreuer Prof. R. Stiefelhagen
Schlagworte Image processing and computer vision, facial image analysis, image alignment, robustness, discriminative models, local feature
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page