Model-based analysis of printed tables
We discuss our system of model-based analysis of printed tables. The goal of our system is to extract and associate parts of a table's image into related segments. For example, we can locate columns, rows, column and table headings of a table's image. The location of these segments are based on features of the table image and on a model of the table. This is a stepwise, top-down approach to table image analysis; thus, for example, the body of the table is located before rows or columns, or individual table cells. The algorithms we discuss involve the stepwise analysis of the image and the grouping of these segments into larger structures (columns, rows, etc.).
Keywordstables model-based analysis top-down analysis
Unable to display preview. Download preview PDF.
- Laurentini, A. and P. Viada, “Identifying and Understanding Tabular Material in Compound Documents,” Proc. ICPR, 1992, pp. 405–409.Google Scholar
- Chandran, S. and R. Kasturi, “Structural Recognition of Tabulated Data,” ICDAR Japan, October 1993, pp. 516–519.Google Scholar
- Watanabe, T., H. Naruse, Q. Luo, N. Sugie, “Structure Analysis of Table-form Documents on the Basis of the Recognition of Vertical and Horizontal Line Segments,” ICDAR France, 1991, pp. 638–646.Google Scholar