Object recognition is a central problem in computer vision research. Most object recognition systems have taken one of two approaches, using either global or local features exclusively. This may be in part due to the difficulty of combining a single global feature vector with a set of local features in a suitable manner. In this paper, we show that combining local and global features is beneficial in an application where rough segmentations of objects are available. We present a method for classification with local features using non-parametric density estimation. Subsequently, we present two methods for combining local and global features. The first uses a "stacking" ensemble technique, and the second uses a hierarchical classification system. Results show the superior performance of these combined methods over the component classifiers, with a reduction of over 20% in the error rate on a challenging marine science application.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Combining Local and Global Image Features for Object Class Recognition


    Beteiligte:
    Lisin, D.A. (Autor:in) / Mattar, M.A. (Autor:in) / Blaschko, M.B. (Autor:in) / Learned-Miller, E.G. (Autor:in) / Benfield, M.C. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    245520 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Local Features for Object Class Recognition

    Mikolajczyk, K. / Leibe, B. / Schiele, B. et al. | British Library Conference Proceedings | 2005


    Local features for object class recognition

    Mikolajczyk, K. / Leibe, B. / Schiele, B. | IEEE | 2005


    Local and global Gabor features for object recognition

    Kamarainen, J. K. / Kyrki, V. / Kälviäinen, H. | British Library Online Contents | 2007


    Traffic sign recognition by combining global and local features based on semi‐supervised classification

    He, Zhenli / Nan, Fengtao / Li, Xinfa et al. | Wiley | 2020

    Freier Zugriff