Face Alignment Using Boosting and Evolutionary Search

Hua Zhang, Duanduan Liu, Mannes Poel, Antinus Nijholt

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

    1 Citation (Scopus)
    77 Downloads (Pure)

    Abstract

    In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.
    Original languageUndefined
    Title of host publicationNinth Asian Conference on Computer Vision (ACCV 2009). Part II
    EditorsH. Zha, R.-I. Taniguchi, S. Maybank
    Place of PublicationBerlin
    PublisherSpringer
    Pages110-119
    Number of pages10
    ISBN (Print)978-3-642-12303-0
    DOIs
    Publication statusPublished - 25 Apr 2010
    Event9th Asian Conference on Computer Vision, ACCV 2009 - Peking University, Xi'an, China
    Duration: 23 Sep 200927 Sep 2009
    Conference number: 9

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Volume5995

    Conference

    Conference9th Asian Conference on Computer Vision, ACCV 2009
    Abbreviated titleACCV
    CountryChina
    CityXi'an
    Period23/09/0927/09/09

    Keywords

    • METIS-270691
    • IR-71163
    • evolutionary search
    • Face alignment
    • EWI-16061
    • granular features
    • boosting appearance models
    • HMI-MI: MULTIMODAL INTERACTIONS
    • EC Grant Agreement nr.: FP6/033812

    Cite this