Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformations, such as rotation, scaling, or affine warping. When patches overlap object boundaries, however, errors in both detection and matching will almost certainly occur due to inclusion of unwanted background pixels. This is common in real images, which often contain significant background clutter, objects which are not heavily textured, or objects which occupy a relatively small portion of the image. We suggest improvements to the popular Scale Invariant Feature Transform (SIFT) which incorporate local object boundary information. The resulting feature detection and descriptor creation processes are invariant to changes in background. We call this method the Background and Scale Invariant Feature Transform (BSIFT). We demonstrate BSIFT's superior performance in feature detection and matching on synthetic and natural images.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Incorporating Background Invariance into Feature-Based Object Recognition


    Beteiligte:
    Stein, Andrew (Autor:in) / Hebert, Martial (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    431854 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Incorporating Object Tracking Feedback into Background Maintenance Framework

    Taycher, Leonid / Fisher III, John W. / Darrell, Trevor | IEEE | 2005


    Incorporating process knowledge into object recognition for assemblies

    Braun, E. / Fritsch, J. / Sagerer, G. | IEEE | 2001


    Incorporating Process Knowledge into Object Recognition for Assemblies

    Braun, E. / Fritsch, J. / Sagerer, G. et al. | British Library Conference Proceedings | 2001


    Object Recognition Using Multiple View Invariance Based on Complex Features

    Kuno, Y. / Takae, O. / Takahashi, T. et al. | British Library Conference Proceedings | 1996


    Appearance-based visual learning and object recognition with illumination invariance

    Ohba, K. / Sato, Y. / Ikeuchi, K. | British Library Online Contents | 2000