Background lines often exist in textual documents. It is important to detect and remove those lines so text can be easily segmented and recognized. A stochastic model is proposed in this paper which incorporates the high level contextual information to detect severely broken lines. We observed that 1) background lines are parallel, and 2) the vertical gaps between any two neighboring lines are roughly equal with small variance. The novelty of our algorithm is we use a HMM model to model the projection profile along the estimated skew angle, and estimate the optimal positions of all background lines simultaneously based on the Viterbi algorithm. Compared with our previous deterministic model based approach [15], the new method is much more robust and detects about 96.8% background lines correctly in our Arabic document database.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Background Line Detection with A Stochastic Model


    Contributors:


    Publication date :

    2003-06-01


    Size :

    250037 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Stochastic approximation for background modelling

    Lopez-Rubio, E. / Luque-Baena, R. M. | British Library Online Contents | 2011



    Motiorr detection with nonstationary background

    Ren, Y. / Chua, C.-S. / Ho, Y.-K. | British Library Online Contents | 2003


    Motion detection with non-stationary background

    Ying Ren, / Chin-Seng Chua, / Yeong-Khing Ho, | IEEE | 2001


    A stochastic conflict detection model revisited

    Blin, Karine / Akian, Marianne / Bonnans, Frederic et al. | AIAA | 2000