We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linking parts to subparts, soft assignment of subparts to parts, and scale invariant keypoint based local features at the lowest level of the hierarchy. The method is designed to efficiently handle categories containing hundreds of redundant local features, such as those returned by current key-point detectors. This robustness allows it to outperform constellation style models, despite their stronger spatial models. The model is initialized by robust bottom-up voting over location-scale pyramids, and optimized by expectation-maximization. Training is rapid, and objects do not need to be marked in the training images. Experiments on several popular datasets show the method's ability to capture complex natural object classes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hierarchical part-based visual object categorization


    Contributors:
    Bouchard, G. (author) / Triggs, B. (author)


    Publication date :

    2005-01-01


    Size :

    339217 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object categorization by learned universal visual dictionary

    Winn, J. / Criminisi, A. / Minka, T. | IEEE | 2005


    Object Categorization by Learned Universal Visual Dictionary

    Winn, J. / Criminisi, A. / Minka, T. et al. | British Library Conference Proceedings | 2005


    Visual Object Categorization with New Keypoint-based AdaBoost Features

    Bdiri, T. / Moutarde, F. / Steux, B. | British Library Conference Proceedings | 2009


    Visual object categorization with new keypoint-based adaBoost features

    Bdiri, Taoufik / Moutarde, Fabien / Steux, Bruno | IEEE | 2009


    Multimodal Object Categorization Based on Hierarchical Dirichlet Process by a Robot

    Nakamura, T. / Araki, T. / Nagai, T. et al. | British Library Online Contents | 2013