In this paper, we describe a method to construct automatically, from a series of images of objects, a model of an object class. The model is described by a set of 2 dimensional features of segmented regions and the relations among them. To make models of objects, we introduce the concept of the segmentation tree-which represents image segmentation at various levels of abstraction-and also a model generation method based on a series of segmentation trees. Using this segmentation tree, we can cope with the problem of diversity of segmentation patterns and can easily make stable object-models.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A model generation method for object recognition task by pictorial examples


    Contributors:
    Arita, D. (author) / Tsuruta, N. (author) / Taniguchi, R. (author) / Amamiya, M. (author)


    Publication date :

    1994-01-01


    Size :

    384167 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Model Generation Method for Object Recognition Task by Pictorial Examples

    Arita, D. / Tsuruta, N. / Taniguchi, R.-I. et al. | British Library Conference Proceedings | 1994


    Pictorial Structures for Object Recognition

    Felzenszwalb, P. F. / Huttenlocher, D. P. | British Library Online Contents | 2005


    Handbook of pictorial symbols : 3250 examples from international sources

    Modley, Rudolf | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 1976