Thumbnail
Access Restriction
Subscribed

Author Sari, T. ♦ Sellami, M.
Sponsorship CEDAR, Univ. Buffalo ♦ Microsoft ♦ Siemens ♦ Hitachi ♦ Motorola ♦ U.S. Postal Service ♦ A2iA ♦ Int. Assoc. Pattern Recognition
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2002
Language English
Subject Domain (in DDC) Technology ♦ Engineering & allied operations ♦ Other branches of engineering
Subject Keyword Optical character recognition software ♦ Dictionaries ♦ Error correction ♦ Hidden Markov models ♦ Speech recognition ♦ Production systems ♦ Knowledge based systems ♦ Natural language processing ♦ Acoustics ♦ Heart
Abstract In this paper we present a contextual-based method for correcting Arabic words generated by OCR systems. This technique operates as a post-processor and it wants to be universal. It corrects substitution and rejection errors. The Arabic language properties are very useful in morpho-lexical analysis and therefore they are strongly exploited in the development of the method. The substitution errors, the most frequently committed ones by the OCR systems, are rewritten in production rules to be used by a rule-based system for correcting Arabic words. The first version of the developed method operates only at the morpho-lexical level, the extension to the other levels of language analysis is considered in perspectives.
Description Author affiliation: Dept. d'Inf., Univ. Badji Mokhtar, Annaba, Algeria (Sari, T.; Sellami, M.)
ISBN 0769516920
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2002-08-06
Publisher Place Canada
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Size (in Bytes) 1.01 MB
Page Count 6
Starting Page 461
Ending Page 466


Source: IEEE Xplore Digital Library