Overview

The purpose of a document is to facilitate the transfer of information from its author to its readers. It is the author's job to design the document so that the information it contains can be interpreted accurately and efficiently. To do this, the author can make use of a set of stylistic tools. We have introduced the concept of document functionality, which attempts to describe the roles of documents and their components in the process of transferring information. A functional description of a document provides insight into the type of the document, into its intended uses, and into strategies for automatic document interpretation and retrieval.

We believe that there is a level of document organization, which can be regarded as intermediate between the geometric and semantic levels, that relates to the efficiency with which the document transfers its information to the reader. This is what we call the functional level.

In order to effectively process a document, most document image understanding systems rely on relatively specific information about a restricted domain in order to accurately model the expected document class(es). This allows the system to richly interpret the document, and extract detailed information about its content. Unfortunately, for less homogeneous environments this approach cannot be effectively applied. As the set or stream of documents becomes more diverse (both intra-class and inter-class), the formulation of models becomes more difficult. Functional interpretation of documents can greatly facilitate tasks associated with their classification and use. We have concentrated on extracting functional features to provide a classification based on how the document can be used.