• DocumentCode
    3498789
  • Title

    Haar features for FACS AU recognition

  • Author

    Whitehill, Jacob ; Omlin, Christian W.

  • Author_Institution
    Dept. of Comput. Sci., Western Cape Univ.
  • fYear
    2006
  • fDate
    2-6 April 2006
  • Lastpage
    101
  • Abstract
    We examined the effectiveness of using Haar features and the Adaboost boosting algorithm for FACS action unit (AU) recognition. We evaluated both recognition accuracy and processing time of this new approach compared to the state-of-the-art method of classifying Gabor responses with support vector machines. Empirical results on the Cohn-Kanade facial expression database showed that the Haar+Adaboost method yields AU recognition rates comparable to those of the Gabor+SVM method but operates at least two orders of magnitude more quickly
  • Keywords
    Haar transforms; face recognition; support vector machines; visual databases; Adaboost boosting algorithm; Cohn-Kanade facial expression database; Gabor responses; Haar features; support vector machines; Boosting; Computer vision; Face detection; Face recognition; Feature extraction; Gold; Object recognition; Pixel; Support vector machine classification; Support vector machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automatic Face and Gesture Recognition, 2006. FGR 2006. 7th International Conference on
  • Conference_Location
    Southampton
  • Print_ISBN
    0-7695-2503-2
  • Type

    conf

  • DOI
    10.1109/FGR.2006.61
  • Filename
    1613004