We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in the data and yield very high classification rates when used with a variety of classifiers trained on small training sets, exhibiting robustness to degradation with clutter. Of particular interest is the use of the features as variables in simple statistical models for the objects thus enabling likelihood based classification. Pre-training decision boundaries between classes, a necessary component of non-parametric techniques, are thus avoided. Class models are trained separately with no need to access data of other classes. Experimental results are presented for handwritten character recognition, classification of deformed BTEX symbols involving hundreds of classes, and side view car detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Part-based statistical models for object classification and detection


    Contributors:
    Bernstein, E.J. (author) / Amit, Y. (author)


    Publication date :

    2005-01-01


    Size :

    465754 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Statistical Models of Object Interaction

    Morris, R. J. / Hogg, D. C. | British Library Online Contents | 2000


    Statistical Multi-Object Shape Models

    Lu, C. / Pizer, S. M. / Joshi, S. et al. | British Library Online Contents | 2007


    Partially Occluded Object Recognition Using Statistical Models

    Ying, Z. / Castanon, D. | British Library Online Contents | 2002


    Statistical context priming for object detection

    Torralba, A. / Sinha, P. | IEEE | 2001


    Statistical Context Priming for Object Detection

    Torralba, A. / Sinha, P. / IEEE | British Library Conference Proceedings | 2001