HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

EXTRAFOR : automatic EXTRAction of mathematical FORmulas

Afef Kacem 1 Abdel Belaid 2 Mohamed Ben Ahmed 1
1 RIADI - Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba]
2 LORIASI - Loria in the Society of Information
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present a method for automatic extraction of mathematical formulas from images of documents without character recognition. Formula extraction is first done by location of its most significant symbols, then extension to adjoining symbols using contextual rules until delimitation of the whole formula space. Mathematical symbols labelling is realised from models created at the learning stage using fuzzy logic. This paper reviews our current efforts to develop such a system, presents problems we have encountered and summarises our results. The average rate of preliminary labelling rate is about 95.3%. 90% of mathematical formulas are well extracted from documents printed with high quality.
Mots-clés : formules mathématiques fuzzy logic mathematical formulas document segmentation segmentation de document logique floue
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/inria-00098838
Contributor : Publications Loria Connect in order to contact the contributor
Submitted on : Tuesday, September 26, 2006 - 8:39:03 AM
Last modification on : Friday, February 4, 2022 - 3:25:31 AM

Identifiers

Collections

INRIA | CNRS | LORIA | UNIV-LORRAINE | INRIA2

Citation

Afef Kacem, Abdel Belaid, Mohamed Ben Ahmed. EXTRAFOR : automatic EXTRAction of mathematical FORmulas. International Conference on Document Analysis & Recognition - ICDAR'99, 1999, Bangalore, India. pp.527-530, ⟨10.1109/ICDAR.1999.791841⟩. ⟨inria-00098838⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

8115

 

Contact                    Legal Notice                    Personal Data