Many document representations are in use. Each representation explicitly encodes different aspects of a document. External document representations, using standard file formats (such as JPEG, postscript, HTML, LaTeX), are used to communicate document-data between programs. Internal document representations are used within document analysis or document production software, to store intermediate results in the transformation from the input to output document representation. These document representations are central to defining and solving document analysis problems. Issues that can be investigated include defining equivalence of documents and distance between documents, mathematically characterizing the mapping between document representations, characterizing the external information needed to carry out these mappings, and characterizing the differences between the forward and inverse mappings that occur during document analysis and document production. From our ongoing investigation of these issues, we present a summary of internal document representations used in the table-recognition literature, and case studies of external document representations in the domains of circuit diagrams and text documents.
Date of creation, presentation, or exhibit
Department, Program, or Center
Computer Science (GCCIS)
Fifth IAPR Int'l Workshop on Graphics Recognition: Proc. GREC. Held at UAB: Barcelona, Spain: 30-31 July 2003 pps. 3-12
RIT – Main Campus