Evaluating AAM fitting methods for facial expression recognition

Akshay Asthana, Jason Saragih, Michael Wagner, Roland Goecke

    Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

    54 Citations (Scopus)
    36 Downloads (Pure)


    The human face is a rich source of information for the viewer and facial expressions are a major component in judging a person's affective state, intention and personality. Facial expressions are an important part of human-human interaction and have the potential to play an equally important part in human-computer interaction. This paper evaluates various active appearance model (AAM) fitting methods, including both the original formulation as well as several state-of-the-art methods, for the task of automatic facial expression recognition. The AAM is a powerful statistical model for modelling and registering deformable objects. The results of the fitting process are used in a facial expression recognition task using a region-based intermediate representation related to action units, with the expression classification task realised using a support vector machine. Experiments are performed for both person-dependent and person-independent setups. Overall, the best facial expression recognition results were obtained by using the iterative error bound minimisation method, which consistently resulted in accurate face model alignment and facial expression recognition even when the initial face detection used to initialise the fitting procedure was poor.
    Original languageEnglish
    Title of host publication3rd International Conference on Affective Computing and Intelligent Interaction and Workshops
    EditorsJeffrey Cohn, Anton Nijholt, Maja Pantic
    Place of PublicationThe Netherlands
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Number of pages8
    ISBN (Print)9781424447992
    Publication statusPublished - 2009
    EventACII 2009 - Amsterdam, Netherlands
    Duration: 10 Sept 200912 Sept 2009


    ConferenceACII 2009


    Dive into the research topics of 'Evaluating AAM fitting methods for facial expression recognition'. Together they form a unique fingerprint.

    Cite this