Description

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

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.

Reuse Permissions
  • 1.08 MB application/pdf

    Download count: 0

    Details

    Contributors
    Date Created
    • 2014
    Resource Type
  • Text
  • Collections this item is in
    Note
    • Partial requirement for: M.S., Arizona State University, 2014
      Note type
      thesis
    • Includes bibliographical references (p. 45-47)
      Note type
      bibliography
    • Field of study: Electrical engineering

    Citation and reuse

    Statement of Responsibility

    by Anirudh Yellamraju

    Machine-readable links