Equivalence of some common linear feature extraction techniques for appearance-based object recognition tasks

M Asuncion Vicente, Patrik O Hoyer, Aapo Hyvärinen

    Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

    Sammanfattning

    Recently, a number of empirical studies have compared the performance of PCA and ICA as feature extraction methods in appearance-based object recognition systems, with mixed and seemingly contradictory results. In this paper, we briefly describe the connection between the two methods and argue that whitened PCA may yield identical results to ICA in some cases. Furthermore, we describe the specific situations in which ICA might significantly improve on PCA.
    Originalspråkengelska
    TidskriftIEEE Transactions on Pattern Analysis and Machine Intelligence
    Volym29
    Utgåva5
    Sidor (från-till)896-900
    Antal sidor5
    ISSN0162-8828
    DOI
    StatusPublicerad - 2007
    MoE-publikationstypA1 Tidskriftsartikel-refererad

    Vetenskapsgrenar

    • 113 Data- och informationsvetenskap

    Citera det här