Abstract

this paper we describe a system that can analyze a wide variety of printed table formats. The adaptability of this system is realized by a model of the table's organization. Printed representations of relational data rely on several kinds of visual clues for imparting the table's logical structure to the reader. For example, ruling lines of various widths might indicate a grouping of consecutive items or attributes. A system reading a table must make deductions based on these visual devices before it is able to specify the relational organization of the table. Some of the visual clues used to logically organize the physically structured information in the table are:

Citations