Corpus ID: 43926975

Detection of Tables in Scanned Document Images

  title={Detection of Tables in Scanned Document Images},
  author={T. Kasar and S. Adams and T. Paquet},
  • T. Kasar, S. Adams, T. Paquet
  • Published 2013
  • The paper presents a method to detect table regions in document images by identifying the column and row lineseparators and their properties. In order to enhance dark thin line-like structures, the input image is first smoothed with a Gaussian filter followed by gray-scale morphological black-hat operation. This pre-processed image is adaptively-thresholded and a run-length approach is employed to extract horizontally and vertically-aligned lines. From each group of intersecting horizontal and… CONTINUE READING

    Figures and Tables from this paper.


    Publications referenced by this paper.
    LIBSVM: A library for support vector machines
    • 36,665
    • PDF
    A simple and effective table detection system from document images
    • 60
    Table detection in heterogeneous documents
    • 75
    • PDF
    Table structure recognition based on robust block segmentation
    • 105
    Trainable table location in document images
    • 41
    Identifying and understanding tabular material in compound documents
    • 48
    Model-based analysis of printed tables
    • 47
    • 2005
    Structure analysis of table-form documents on the basis of the recognition of vertical and horizontal line segments
    • 1991