We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized correlograms that integrate both information of local parts and their spatial relations. Incorporating the spatial relations into our constellation of descriptors, we show that an exhaustive search for the best matching can be avoided. Combining the contextual descriptors with boosting, the system simultaneously learns the information that characterize each part of the object along with their characteristic mutual spatial relations. The proposed framework includes a matching step between homologous parts in the training set, and learning the spatial pattern after matching. In the matching part two approaches are provided: a supervised algorithm and an unsupervised one. Our results are favorably compared against state-of-the-art results.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fast spatial pattern discovery integrating boosting with constellations of contextual descriptors


    Beteiligte:
    Amores, J. (Autor:in) / Sebe, N. (Autor:in) / Radeva, P. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    476546 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Pattern Recognition of Star Constellations

    Leibe | Online Contents | 1993


    Analyzing Ancient Maya Glyph Collections with Contextual Shape Descriptors

    Roman-Rangel, E. / Pallan, C. / Odobez, J. M. et al. | British Library Online Contents | 2011