Filtreler

2015 - 20182
Filtreleri Sıfırla

Ayarlar

Yazar: Ağdoğan, Didem × Konu: Facial expression ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Yayın
    Mathematical modeling of human facial muscles
    (Işık Üniversitesi, 2015-08-10) Ağdoğan, Didem; Eskil, Mustafa Taner; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programı
    In this study; a new muscle model is proposed for computation of actual muscle forces that exist during facial expressions. Modeling of facial muscle forces is done on the expression of surprise. We choose this expression as it is performed by the activation of a single(frontalis) muscle. Videos used in the study are recorded with a high resolution camera where the subject's face was painted with a rectangular grid. The first and last frames of subject's surprise expression is used for extraction of muscle forces. Feature points which are located in the first frame are manually marked on the last frame with guidance of the rectangular grid. Muscle forces that are exerted on the facial skin are computed using a massspring model and an anatomical muscle model is derived. Skin is also modelled as a nonlinear deformable tissue for more realistic results. The accuracy of the proposed model is shown through simulations.
  • Küçük Resim
    Yayın
    An observation based muscle model for simulation of facial expressions
    (Elsevier Science BV, 2018-05) Erkoç, Tuğba; Ağdoğan, Didem; Eskil, Mustafa Taner
    This study presents a novel facial muscle model for coding of facial expressions. We derive this model from unintrusive observation of human subjects in the progress of the surprise expression. We use a generic and single-layered face model which embeds major muscles of the human face. This model is customized onto the human subject's face on the first frame of the video. The last frame of the video is used to project a set of manually marked feature points to estimate the 3 dimensional displacements of vertices due to facial expression. Vertex displacements are used in a mass spring model to estimate the external forces, i.e. the muscle forces on the skin. We observed that the distribution of muscle forces resemble sigmoid or hyperbolic tangent functions. We chose hyperbolic tangent function as our base model and parameterized it using least squares. We compared the proposed muscle model with frequently used models in the literature.