We present a framework for learning object representations for fast recognition of a large number of different objects. Rather than learning and storing feature representations separately for each object, we create a finite set of representative features and share these features within and between different object models. In contrast to traditional recognition methods that scale linearly with the number of objects, the shared features can be exploited by bottom-up search algorithms which require a constant number of feature comparisons for any number of objects. We demonstrate the feasibility of this approach on a novel database of 50 everyday objects in cluttered real-world scenes. Using Gabor wavelet-response features extracted only at corner points, our system achieves good recognition results despite substantial occlusion and background clutter.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Shared Features for Scalable Appearance-Based Object Recognition


    Contributors:


    Publication date :

    2005-01-01


    Size :

    394774 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Appearance-based active object recognition

    Borotschnig, H. / Paletta, L. / Prantl, M. et al. | British Library Online Contents | 2000


    Appearance-based object recognition using multiple views

    Selinger, A. / Nelson, R.C. | IEEE | 2001




    Appearance-Based Object Recognition Using Multiple Views

    Selinger, A. / Nelson, R. C. / IEEE | British Library Conference Proceedings | 2001