Psychological research for the recognition of emotions from facial expressions have evolved over the years. Recent technological advances in imaging, computing, computer vision, and pattern recognition have paved the way for automating facial expression recognition. The proposed approach in this paper presents our initial expression classification research using Hidden Markov Models (HMM) on 2D texture facial data. A surface curvature based feature extraction technique involving geometric facial data from unique 3D sensors is also being investigated. It is expected that the proposed methodologies could provide significant improvements in facial expression and emotion recognition performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Facial expression analysis using 2D and 3D features


    Beteiligte:


    Erscheinungsdatum :

    01.07.2011


    Format / Umfang :

    4022270 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Drowsiness detection using facial expression features

    Hachisuka, Satori / Kumura, Teiyuu / Ishida, Kenji et al. | Tema Archiv | 2010


    Drowsiness Detection Using Facial Expression Features

    Nakatani, Hiroto / Ishida, Kenji / Ozaki, Noriyuki et al. | SAE | 2010


    Drowsiness detection using facial expression features

    Hachisuka,S. / Kimura,T. / Ishida,K. et al. | Kraftfahrwesen | 2010


    Authentic facial expression analysis

    Sebe, N. / Lew, M. S. / Sun, Y. et al. | British Library Online Contents | 2007


    Features classification using support vector machine for a facial expression recognition system

    Patil, R.A. / Sahula, V. / Mandal, A.S. | British Library Online Contents | 2012