Both example-based and model-based approaches for classifying contour shapes can encounter difficulties when dealing with classes that have large nonlinear variability, especially when the variability is structural or due to articulation. This paper proposes a part-based approach to address this problem. Bayesian classification is performed within a three-level framework, which consists of models for contour segments, for classes, and for the entire database of training examples. The class model enables different parts of different exemplars of a class to contribute to the recognition of an input shape. The method is robust to occlusion and is invariant to planar rotation, translation, and scaling. Furthermore, the method is completely automated. It achieves 98% classification accuracy on a large database with many classes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Classification of contour shapes using class segment sets


    Contributors:
    Sun, K.B. (author) / Super, B.J. (author)


    Publication date :

    2005-01-01


    Size :

    300118 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluating contour segment descriptors

    Yang, C. / Tiebe, O. / Shirahama, K. et al. | British Library Online Contents | 2017


    Object Detection by Contour Segment Networks

    Ferrari, V. / Tuytelaars, T. / Van Gool, L. | British Library Conference Proceedings | 2006


    CONTOUR CLASS DIVIDER

    PAPKE ROBERT / CLAFLIN SHAWN / MCKEE JEFFEREY M et al. | European Patent Office | 2021

    Free access

    Contour class divider

    PAPKE ROBERT / CLAFLIN SHAWN / MCKEE JEFFEREY M et al. | European Patent Office | 2023

    Free access

    CONTOUR CLASS DIVIDER

    PAPKE ROBERT / CLAFLIN SHAWN / MCKEE JEFFEREY et al. | European Patent Office | 2024

    Free access