We present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, length, and symmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. The recognition procedure is formulated as a training procedure made by recursive neural networks followed by a testing procedure over unknown tree structured patterns.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Shape recognition by distributed recursive learning of multiscale trees


    Contributors:


    Publication date :

    2003-01-01


    Size :

    409008 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Distributed recursive learning for shape recognition through multiscale trees

    Lombardi, L. / Petrosino, A. | British Library Online Contents | 2007


    Shape Recognition by Distributed Recursive Learning of Multiscale Trees

    Lombardi, L. / Petrosino, A. / IEEE | British Library Conference Proceedings | 2003


    Shape Recognition Using Recursive Mathematical Morphology

    Schauf, M. / Haralick, R. M. / University of Naples et al. | British Library Conference Proceedings | 1997


    Shape Representation and Recognition from Multiscale Curvature

    Dudek, G. / Tsotsos, J. K. | British Library Online Contents | 1997