Using Two-Class Classifiers for Multiclass Classification

DMJ Tax, RPW Duin

    Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

    183 Citations (Scopus)


    The generalization from two-class classification to multiclass classification is not straightforward for discriminants which are not based on density estimation. Simple combining methods use voting, but this has the drawback of inconsequent labelings and ties. More advanced methods map the discriminant outputs to approximate posterior probability estimates and combine these, while other methods use error-correcting output codes. In this paper we want to show the possibilities of simple generalizations of the twoclass classification, using voting and combinations of approximate posterior probabilities.
    Original languageUndefined/Unknown
    Title of host publicationICPR16, Proceedings
    EditorsR Kasturi, D Laurendeau, C Suen
    Place of PublicationLos Alamitos, CA
    Number of pages4
    ISBN (Print)0-7695-1696-3
    Publication statusPublished - 2002
    Event16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II - Los Alamitos, CA
    Duration: 11 Aug 200215 Aug 2002

    Publication series

    PublisherIEEE Computer Society Press
    NameInternational Conference on Pattern Recognition
    ISSN (Print)1051-4651


    Conference16th International Conference on Pattern Recognition (Quebec City, Canada), vol. II

    Bibliographical note

    ISSN 1051-4651, phpub 41


    • conference contrib. refereed
    • Conf.proc. > 3 pag

    Cite this