Thick 2D relations for document understanding

Marco Aiello*, Arnold M W Smeulders

*Corresponding author for this work

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We use a prepositional language of qualitative rectangle relations to detect the reading order from document images. To this end, we define the notion of a document encoding rule and we analyze possible formalisms to express document encoding rules such as LaTeX and SGML. Document encoding rules expressed in the propositional language of rectangles are used to build a reading order detector for document images. In order to achieve robustness and avoid brittleness when applying the system to real life document images, the notion of a thick boundary interpretation for a qualitative relation is introduced. The framework is tested on a collection of heterogeneous document images showing recall rates up to 89%.

Original languageEnglish
Pages (from-to)147-176
Number of pages30
JournalInformation Sciences
Volume167
Issue number1-4
DOIs
Publication statusPublished - 2 Dec 2004
Externally publishedYes

Keywords

  • Bidimensional Allen relations
  • Constraint satisfaction: applications
  • Document image analysis
  • Document understanding
  • Spatial reasoning

Fingerprint Dive into the research topics of 'Thick 2D relations for document understanding'. Together they form a unique fingerprint.

Cite this