A general-purpose object indexing technique is described that combines the virtues of principal component analysis with the favorable matching properties of high-dimensional spaces to achieve high-precision recognition. An object is represented by a set of high-dimensional iconic feature vectors comprised of the responses of derivatives of Gaussian filters at a range of orientations and scales. Since these filters can be shown to form the eigenvectors of arbitrary images containing both natural and man-made structures, they are well-suited for indexing in disparate domains. The indexing algorithm uses an active vision system in conjunction with a modified form of Kanerva's (1988, 1993) sparse distributed memory which facilitates interpolation between views and provides a convenient platform for learning the association between an object's appearance and its identity. The robustness of the indexing method was experimentally confirmed by subjecting the method to a range of viewing conditions and the accuracy was verified using a well-known model database containing a number of complex 3D objects under varying pose.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object indexing using an iconic sparse distributed memory


    Contributors:
    Rao, R.P.N. (author) / Ballard, D.H. (author)


    Publication date :

    1995-01-01


    Size :

    1039133 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object Indexing Using an Iconic Sparse Distributed Memory

    Rao, R. / Ballard, D. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995


    Iconic paper

    Peairs, M. | IEEE | 1995


    Iconic Paper

    Peairs, M. | British Library Conference Proceedings | 1995


    Volkswagen Up!, iconic simplicity

    Baruffaldi, Silvia | Online Contents | 2008