In this thesis we consider the problem of facial expression recognition (FER) from video sequences. Our method is based on subspace representations and Grassmann manifold based learning. We use Local Binary Pattern (LBP) at the frame level for representing the facial features. Next we develop a model to represent the video sequence in a lower dimensional expression subspace and also as a linear dynamical system using Autoregressive Moving Average (ARMA) model.
Download count: 0
- Partial requirement for: M.S., Arizona State University, 2014Note typethesis
- Includes bibliographical references (p. 45-47)Note typebibliography
- Field of study: Electrical engineering