This article develops an analogy between object recognition and the transmission of information through a channel based on the statistical representation of the appearances of 3D objects. This analogy provides a means to quantitatively evaluate the contribution of individual receptive field vectors, and to predict the performance of the object recognition process. Transinformation also provides a quantitative measure of the discrimination provided by each viewpoint, thus permitting the determination of the most discriminant viewpoints. As an application, the article develops an active object recognition algorithm which is able to resolve ambiguities inherent in a single-view recognition algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Transinformation for active object recognition


    Contributors:
    Schiele, B. (author) / Crowley, J.L. (author)


    Publication date :

    1998-01-01


    Size :

    746998 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Transinformation for Active Object Recognition

    Schiele, B. / Crowley, J. L. / IEEE; Computer Society | British Library Conference Proceedings | 1998



    Active/space-variant object recognition

    Tistarelli, M. | British Library Online Contents | 1995


    Appearance-based active object recognition

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


    Active Object Recognition: Looking for Differences

    Callari, F. G. / Ferrie, F. P. | British Library Online Contents | 2001