Spectral Spatial Gradients (SSGs) have been suggested as features invariant to illumination variation for color-based recognition and indexing. While SSGs have a greater degree of invariance than Spectral Gradients (SGs), they may have a reduced discrimination power between objects since they use only spatial changes of object reflectance. The approach presented is to use the framework of SGs and SSGs to create a recognition method which is invariant to varying illumination without discarding the reflectance distribution information. Two techniques are used to extract the varying illumination. The first is to assume that low-frequency SG variation is due to illumination. The second method uses regions with matching SSGs to get local estimates of illumination. Once the local illumination variation has been extracted, its effect on the SGs can be removed and the resulting Adapted Spectral Gradients (ASGs) have a greater power of discrimination for some objects than SSG features. Experimental results demonstrate cases where ASGs show improved performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Increasing the discrimination power of Spectral Spatial Gradients


    Beteiligte:
    Berwick, D. (Autor:in) / Sang Wook Lee, (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    758929 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Increasing the Discrimination Power of Spectral Spatial Gradients

    Berwick, D. / Lee, S. W. / IEEE | British Library Conference Proceedings | 2001



    Effect of spatial wind gradients on airplane aerodynamics

    VICROY, DAN D. / BOWLES, ROLAND L. | AIAA | 1989


    Effect of spatial wind gradients on airplane aerodynamics

    Vicroy, Dan D. / Bowles, Roland L. | NTRS | 1989


    Spectral gradients for color-based object recognition and indexing

    Berwick, D. / Lee, S. W. | British Library Online Contents | 2004