Previous efforts at facial expression recognition have been based on the Facial Action Coding System (FACS), a representation developed in order to allow human psychologists to code expression from static facial "mugshots." We develop new more accurate representations for facial expression by building a video database of facial expressions and then probabilistically characterizing the facial muscle activation associated with each expression using a detailed physical model of the skin and muscles. This produces a muscle based representation of facial motion, which is then used to recognize facial expressions in two different ways. The first method uses the physics based model directly, by recognizing expressions through comparison of estimated muscle activations. The second method uses the physics based model to generate spatio temporal motion energy templates of the whole face for each different expression. These simple, biologically plausible motion energy "templates" are then used for recognition. Both methods show substantially greater accuracy at expression recognition than has been previously achieved.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Facial expression recognition using a dynamic model and motion energy


    Contributors:
    Essa, I.A. (author) / Pentland, A.P. (author)


    Publication date :

    1995-01-01


    Size :

    983465 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Facial Expression Recognition Using a Dynamic Model and Motion Energy

    Essa, I. / Pentland, A. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995



    Facial Expression Recognition Using Continuous Dynamic Programming

    Zhang, H. / Guo, Y. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2001


    View and Texture-Independent Facial Expression Recognition in Videos using Dynamic Programming

    Dornaika, F. / Davoine, F. | British Library Conference Proceedings | 2005