Tables are compact and efficient means for representing information. Automatic table structure extraction is a challenging problem in the field of document layout analysis. In this paper, an automatic table detection and cell extraction using image morphological operations proposed. The proposed system comprises of four distinct steps. Corners and line intersections identification step, which detects the four outer corners and all the inner line intersections using nine structuring elements. Textual elements present in the table may create false corners and line intersections, which affects the identification of cells in a table. The proposed system introduced two methods namely, the intersection operation between structuring elements followed by a projection profile for removing false corners and line intersection in the noise removal step. Finally, cells in a table are identified using connected components. Our proposed system is tested on tables without textual information, tables with textual information, tables with increased line thickness and tables with no rows and column lines under diverse background and various sizes. The result shows our proposed system provides better results. © 2017, Institute of Advanced Scientific Research, Inc. All rights reserved.
cited By 0
S. Sindhuja and A. Baskar, “An automatic table detection and cell extraction using image morphological operations”, Journal of Advanced Research in Dynamical and Control Systems, vol. 9, no. Special issue 11, pp. 184-193, 2017.