We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of 15 objects under clutter and occlusion.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Object-specific figure-ground segregation


    Contributors:
    Yu, S.U. (author) / Jianbo Shi, (author)


    Publication date :

    2003-01-01


    Size :

    946970 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Object-Specific Figure-Ground Segregation

    Yu, S. / Shi, J. / IEEE | British Library Conference Proceedings | 2003


    A Model of Figure-Ground Segregation from Kinetic Occlusion

    Chou, G. / IEEE Computer Society / Technical Committee on Pattern Analysis and Machine Intelligence | British Library Conference Proceedings | 1995




    Segmentation by Color Coalition Labeling for Figure-Ground Segregation in Decoration Designs

    Huiskes, M. J. / Pauwels, E. J. / IEEE | British Library Conference Proceedings | 2003