Automatic document processing: A survey

Yuan Y. Tang, Seong Whan Lee, Ching Y. Suen

Research output: Contribution to journalArticlepeer-review

38 Citations (Scopus)


Surveys of the basic concepts and underlying techniques are presented in this paper. A basic model for document processing is described. In this model, document processing can be divided into two phases: document analysts and document understanding. A document has two structures: geometric (layout) structure and logical structure. Extraction of the geometric structure from a document refers to document analysis; mapping the geometric structure into logical structure deals with document understanding. Both types of document structures and the two areas of document processing are discussed. Two categories of methods have been used in document analysis, namely, (1) hierarchical methods including top-down and bottom-up approaches, (2) no-hierarchical methods including modified fractal signature. Tree transform, formatting knowledge and description language approaches have been used in document understanding. A particular case of form document processing is discussed. Form description and form registration approaches are presented. A form processing system is also introduced. Finally, many techniques, such as skew detection, Hough transform, Gabor filters, projection, crossing counts, form definition language, etc. which have been used in these approaches are discussed.

Original languageEnglish
Pages (from-to)1931-1952
Number of pages22
JournalPattern Recognition
Issue number12
Publication statusPublished - 1996 Dec


  • Description languages
  • Document analysis and understanding
  • Document processing
  • Formatting knowledge
  • Geometric and logical structures
  • Hierarchical and no-hierarchical methods
  • Texture analysis
  • Tree transform

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Automatic document processing: A survey'. Together they form a unique fingerprint.

Cite this