Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) recently evaluated a variety of approaches and identified the SIFT [D. G. Lowe, 1999] algorithm as being the most resistant to common image deformations. This paper examines (and improves upon) the local image descriptor used by SIFT. Like SIFT, our descriptors encode the salient aspects of the image gradient in the feature point's neighborhood; however, instead of using SIFT's smoothed weighted histograms, we apply principal components analysis (PCA) to the normalized gradient patch. Our experiments demonstrate that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation. We also present results showing that using these descriptors in an image retrieval application results in increased accuracy and faster matching.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    PCA-SIFT: a more distinctive representation for local image descriptors


    Beteiligte:
    Yan Ke, (Autor:in) / Sukthankar, R. (Autor:in)


    Erscheinungsdatum :

    2004-01-01


    Format / Umfang :

    631716 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    PCA-SIFT: A More Distinctive Representation for Local Image Descriptors

    Ke, Y. / Sukthankar, R. / IEEE Computer Society | British Library Conference Proceedings | 2004


    GOLD: Gaussians of Local Descriptors for image representation

    Serra, G. / Grana, C. / Manfredi, M. et al. | British Library Online Contents | 2015


    Jet-Based Local Image Descriptors

    Larsen, A.B.L. / Darkner, S. / Dahl, A.L. et al. | British Library Conference Proceedings | 2012


    Matching local image feature descriptors

    Europäisches Patentamt | 2020

    Freier Zugriff