Using White Space for Automated Document Structuring

We present and analyze efficient algorithms for the automated recognition and interpretation of layout structures in electronic documents. The key idea is to use the patterns in the distribution of white space in a document to recognize and interpret its components. The recognition algorithm divides the document into a hierarchy of logical elements; the interpretation algorithms classify these divisions as base-text, tables, indented lists, polygonal drawings, and graphs. We present experimental data and discuss an information access application. Our methodology allows the automatic markup of documents\footnote{For instance in the SGML format} and the creation of multi-level indices and browsing tools for electronic libraries.