Regression-based Multi-View Facial Expression Recognition

Ognjen Rudovic, Ioannis Patras, Maja Pantic

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    37 Citations (Scopus)
    14 Downloads (Pure)

    Abstract

    We present a regression-based scheme for multi-view facial expression recognition based on 2蚠D geometric features. We address the problem by mapping facial points (e.g. mouth corners) from non-frontal to frontal view where further recognition of the expressions can be performed using a state-of-the-art facial expression recognition method. To learn the mapping functions we investigate four regression models: Linear Regression (LR), Support Vector Regression (SVR), Relevance Vector Regression (RVR) and Gaussian Process Regression (GPR). Our extensive experiments on the CMU Multi- PIE facial expression database show that the proposed scheme outperforms view-specific classifiers by utilizing considerably less training data.
    Original languageUndefined
    Title of host publicationProceedings of the 20th International Conference on Pattern Recognition, ICPR 2010
    Place of PublicationUSA
    PublisherIEEE Computer Society
    Pages4121-4124
    Number of pages4
    ISBN (Print)978-0-7695-4109-9
    DOIs
    Publication statusPublished - 26 Aug 2010
    Event20th International Conference on Pattern Recognition 2010 - Istanbul Convention & Exhibition Centre, Istanbul, Turkey
    Duration: 23 Aug 201026 Aug 2010
    Conference number: 20
    https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=16097

    Publication series

    Name
    PublisherIEEE Computer Society

    Conference

    Conference20th International Conference on Pattern Recognition 2010
    Abbreviated titleICPR 2010
    CountryTurkey
    CityIstanbul
    Period23/08/1026/08/10
    Internet address

    Keywords

    • METIS-276346
    • IR-75896
    • EWI-19508
    • HMI-MI: MULTIMODAL INTERACTIONS
    • EC Grant Agreement nr.: FP7/211486

    Cite this