Object detection in unconstrained images is an important image understanding problem with many potential applications. There has been little success in creating a single algorithm that can detect arbitrary objects in unconstrained images; instead, algorithms typically must be customized for each specific object. Consequently, it typically requires a large number of exemplars (for rigid objects) or a large amount of human intuition (for non-rigid objects) to develop a robust algorithm. We present a robust algorithm designed to detect a class of compound color objects given a single model image. A compound color object is defined as having a set of multiple, particular colors arranged spatially in a particular way, including flags, logos, cartoon characters, people in uniform, etc. Our approach is based on a particular type of spatial-color joint probability function called the color edge cooccurrence histogram (CECH). In addition, our algorithm employs perceptual color naming to handle color variation, and pre-screening to limit the search scope (i.e., size and location) of the object. Experimental results demonstrated that the proposed algorithm is insensitive to object rotation, scaling, partial occlusion, and folding, outperforming a closely related algorithm by a decisive margin.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Robust color object detection using spatial-color joint probability functions


    Beteiligte:
    Crandall, D. (Autor:in) / Jiebo Luo, (Autor:in)


    Erscheinungsdatum :

    01.01.2004


    Format / Umfang :

    491639 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Robust Color Object Detection Using Spatial-Color Joint Probability Functions

    Crandall, D. / Luo, J. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Affine object tracking with kernel-based spatial-color representation

    Haihong Zhang, / Weimin Huang, / Zhiyong Huang, et al. | IEEE | 2005


    Color Eigenflows: Statistical Modeling of Joint Color Changes

    Miller, E. / Tieu, K. / IEEE | British Library Conference Proceedings | 2001


    Object Based Segmentation of Video Using Color, Motion and Spatial Information

    Khan, S. / Shah, M. / IEEE | British Library Conference Proceedings | 2001