MURAL - Maynooth University Research Archive Library



    Automatic estimation of the dynamics of facial expression using a three-level model of intensity


    Delannoy, Jane Reilly and McDonald, John (2008) Automatic estimation of the dynamics of facial expression using a three-level model of intensity. In: FG '08. 8th IEEE International Conference on Automatic Face & Gesture Recognition, 2008. IEEE, pp. 1-6. ISBN 9781424421534

    [img]
    Preview
    Download (313kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    Facial expressions and their associated dynamics play an important role in human communication. The dynamics of facial expressions can be defined as the intensity and timing of their constituent components as they form. However, estimating the dynamics of facial expressions is a non trivial task. The majority of automatic approaches to characterising intensity use a two-level model (also known as onset-apex-offset). However the FACS specifies five intensity levels for each AU. In this paper we evaluate the efficacy of Local Linear Embedding as a means of estimating the intensity of facial expression. This is done using both the full five level FACS model, and a simplified three level model. We have found that using the FACS intensity scoring results in a considerable overlap between the estimated intensities. Using a three level model enables us to classify the intensities with significantly greater degree of accuracy.

    Item Type: Book Section
    Keywords: face recognition; Local Linear Embedding; facial expression; human communication; onset-apex-offset; local linear embedding;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Item ID: 8341
    Identification Number: https://doi.org/10.1109/AFGR.2008.4813351
    Depositing User: John McDonald
    Date Deposited: 15 Jun 2017 15:56
    Publisher: IEEE
    Refereed: Yes
    Funders: Science Foundation Ireland
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year