Many computer vision problems, such as figure-ground segmentation, simultaneous fitting of curves, selection of an optimal set of geometric primitives, can be formulated naturally as discrete optimization problems. The statement of these problems is relatively easy, but to find techniques that efficiently solve them constitutes a major challenge. In this paper the authors focus on figure-ground segmentation. The authors present a Tabu search strategy which is able to solve the discrete optimization problem associated with figure-ground segmentation in a very efficient way. The resulting deterministic algorithm outperforms the currently fastest known algorithm to solve this problem (mean field annealing) by two orders of magnitude in speed and in addition it consistently finds better optima.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Figure-ground segmentation using Tabu search


    Contributors:


    Publication date :

    1995-01-01


    Size :

    643372 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Figure-Ground Segmentation Using Tabu Search

    Stricker, M. / Leonardis, A. / IEEE; Computer Society; Technical Committee for Pattern Analysis and Machine Intelligence | British Library Conference Proceedings | 1995


    Using Tabu Search for Segmentation of Cursive Handwriting

    Elliman, D. / Bai, L. / Institution of Electrical Engineers et al. | British Library Conference Proceedings | 1999


    Figure-ground segmentation using factor graphs

    Shen, H. / Coughlan, J. / Ivanchenko, V. | British Library Online Contents | 2009


    Clustering Using Tabu Search

    Lin, W.-J. / Lin, J.-C. | British Library Online Contents | 1997


    Optimal Power Flow Using Tabu Search Algorithm

    Abido, M.A. | Online Contents | 2002