We propose a novel framework to build descriptors of local intensity that are invariant to general deformations. In this framework, an image is embedded as a 2D surface in 3D space, with intensity weighted relative to distance in x-y. We show that as this weight increases, geodesic distances on the embedded surface are less affected by image deformations. In the limit, distances are deformation invariant. We use geodesic sampling to get neighborhood samples for interest points, and then use a geodesic-intensity histogram (GIH) as a deformation invariant local descriptor. In addition to its invariance, the new descriptor automatically finds its support region. This means it can safely gather information from a large neighborhood to improve discriminability. Furthermore, we propose a matching method for this descriptor that is invariant to affine lighting changes. We have tested this new descriptor on interest point matching for two data sets, one with synthetic deformation and lighting change, and another with real non-affine deformations. Our method shows promising matching results compared to several other approaches.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deformation invariant image matching


    Beteiligte:
    Haibin Ling, (Autor:in) / Jacobs, D.W. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    708959 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deformation Invariant Image Matching

    Ling, H. / Jacobs, D. / IEEE | British Library Conference Proceedings | 2005


    Scale invariant and deformation tolerant partial shape matching

    Michel, D. / Oikonomidis, I. / Argyros, A. | British Library Online Contents | 2011



    Illumination Invariant Image Matching for Lunar TRN

    Rothenberger, Noah / Georgakis, Georgios / Cheng, Yang et al. | AIAA | 2025