Pose and Expression Recognition Using Limited Feature Points Based on a Dynamic Bayesian Network - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Pose and Expression Recognition Using Limited Feature Points Based on a Dynamic Bayesian Network

Wei Zhao
  • Fonction : Auteur
  • PersonId : 1016738
Goo-Rak Kwon
  • Fonction : Auteur
  • PersonId : 1016739
Sang-Woong Lee
  • Fonction : Auteur
  • PersonId : 1010600

Résumé

In daily life, language is an important tool during the communications between people. Except the language, facial actions can also provide a lot of information. Therefore, facial actions recognition becomes a popular research topic in Human-Computer Interaction (HCI) field. However, it is always a challenging task because of its complexity. In a literal sense, there are thousands of facial muscular movements many of which have very subtle differences. Moreover, muscular movements always occur spontaneously when the pose is changed.To address this problem, firstly we build a fully automatic facial points detection system based on local Gabor filter bank and Principal Component Analysis (PCA). Then the Dynamic Bayesian networks (DBNs) are proposed to perform facial actions recognition using junction tree algorithm over a limited number of feature points. In order to evaluate the proposed method, we have applied the Korean face database for model training, and CUbiC FacePix, FEED, and our own database for testing. Experiment results clearly demonstrate the feasibility of the proposed approach.
Fichier principal
Vignette du fichier
978-3-642-23300-5_18_Chapter.pdf (564.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01590396 , version 1 (19-09-2017)

Licence

Paternité

Identifiants

Citer

Wei Zhao, Goo-Rak Kwon, Sang-Woong Lee. Pose and Expression Recognition Using Limited Feature Points Based on a Dynamic Bayesian Network. 1st Availability, Reliability and Security (CD-ARES), Aug 2011, Vienna, Austria. pp.228-242, ⟨10.1007/978-3-642-23300-5_18⟩. ⟨hal-01590396⟩
38 Consultations
41 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More