Publication

Thick 2D relations for document understanding

Aiello, M. & Smeulders, A. M. W., 2004, In : Information Sciences. 167, p. 147-176 30 p.

Research output: Contribution to journalArticleAcademic

APA

Aiello, M., & Smeulders, A. M. W. (2004). Thick 2D relations for document understanding. Information Sciences, 167, 147-176. https://doi.org/10.1016/j.ins.2003.05.015

Author

Aiello, Marco ; Smeulders, Arnold M.W. / Thick 2D relations for document understanding. In: Information Sciences. 2004 ; Vol. 167. pp. 147-176.

Harvard

Aiello, M & Smeulders, AMW 2004, 'Thick 2D relations for document understanding', Information Sciences, vol. 167, pp. 147-176. https://doi.org/10.1016/j.ins.2003.05.015

Standard

Thick 2D relations for document understanding. / Aiello, Marco; Smeulders, Arnold M.W.

In: Information Sciences, Vol. 167, 2004, p. 147-176.

Research output: Contribution to journalArticleAcademic

Vancouver

Aiello M, Smeulders AMW. Thick 2D relations for document understanding. Information Sciences. 2004;167:147-176. https://doi.org/10.1016/j.ins.2003.05.015


BibTeX

@article{611e3989b54d47d488de256af7258253,
title = "Thick 2D relations for document understanding",
abstract = "We use a propositional 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{\%}.",
keywords = "Constraint satisfaction: applications, Bidimensional Allen relations, Spatial reasoning, Document understanding, Document image analysis",
author = "Marco Aiello and Smeulders, {Arnold M.W.}",
note = "Relation: https://www.rug.nl/informatica/organisatie/overorganisatie/iwi Rights: University of Groningen. Research Institute for Mathematics and Computing Science (IWI)",
year = "2004",
doi = "10.1016/j.ins.2003.05.015",
language = "English",
volume = "167",
pages = "147--176",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Thick 2D relations for document understanding

AU - Aiello, Marco

AU - Smeulders, Arnold M.W.

N1 - Relation: https://www.rug.nl/informatica/organisatie/overorganisatie/iwi Rights: University of Groningen. Research Institute for Mathematics and Computing Science (IWI)

PY - 2004

Y1 - 2004

N2 - We use a propositional 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%.

AB - We use a propositional 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%.

KW - Constraint satisfaction: applications

KW - Bidimensional Allen relations

KW - Spatial reasoning

KW - Document understanding

KW - Document image analysis

U2 - 10.1016/j.ins.2003.05.015

DO - 10.1016/j.ins.2003.05.015

M3 - Article

VL - 167

SP - 147

EP - 176

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -

ID: 14407231