A DTD Extension for Document Structure Recognition

. This paper deals with the representation of document models used in the field of document recognition. A novel formalism called generalized n-gram is presented, which is shown to be accurate for the recognition task and well adapted to automatic learning by examples. The paper addresses also the thorny problem of integrating models for document analysis with existing standards used for document manipulation and production. 1 Introduction The benefits of using high level descriptions to handle structured documents has been widely recognized by the scientific community dealing with electronic document production. The SGML language providing the DTD mechanism [11] has become increasingly important during the last five years. The document analysis and recognition community has been dealing with structure recognition for several years too [4, 7, 1]. In this context, the use of general knowledge, often referred to as document models, describing the document class to be processed is essent..