This paper investigates applications of a new representation for images, the similarity template. A similarity template is a probabilistic representation of the similarity of pixels in an image patch. It has application to detection of a class of objects, because it is reasonably invariant to the color of a particular object. Further, it enables the decomposition of a class of objects into component parts over which robust statistics of color can be approximated. These regions can be used to create a factored color model that is useful for recognition. Detection results are shown on a system that learns to detect a class of objects (pedestrians) in static scenes based on examples of the object provided automatically by a tracking system. Applications of the factored color model to image indexing and anomaly detection are pursued on a database of images of pedestrians.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Similarity templates for detection and recognition


    Contributors:
    Stauffer, C. (author) / Grimson, E. (author)


    Publication date :

    2001-01-01


    Size :

    1717473 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Similarity Templates for Detection and Recognition

    Stauffer, C. / Grimson, E. / IEEE | British Library Conference Proceedings | 2001


    Real-Time Recognition of Activity Using Temporal Templates

    Bobick, A. / Davis, J. / IEEE | British Library Conference Proceedings | 1996



    Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates

    Kumano, S. / Otsuka, K. / Yamato, J. et al. | British Library Online Contents | 2009


    Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates

    Kumano, Shiro / Otsuka, Kazuhiro / Yamato, Junji et al. | Springer Verlag | 2007