Title: A new large Arabic database for offline handwriting recognition

Authors: Maamar Kef; Leila Chergui; Salim Chikhi

Addresses: Department of Computer Sciences, University Hadj Lakhder, Street Chahid Boukhlouf, Batna 05000, Algeria ' Department of Computer Sciences, University Larbi Ben Mhidi, Street 1 Novembre 1945, Oum El Bouaghi 04000, Algeria ' Department of Computer Sciences, University Mentouri, B.P. 325 Street Ain El Bey, Constantine 25017, Algeria

Abstract: To evaluate the performances of handwriting recognition systems, it is necessary to compare them objectively on the same database. A few freely databases are available for Arabic handwriting recognition, for this reason we have developed a new database of Algerian village names to be available freely for research and academic use. Up to now the database contains 1,209 forms including 26,580 binary and greyscale images representing 886 Algerian village names, collected from 1,209 writers. We also describe a new character segmentation algorithm for offline handwritten Arabic words. This algorithm uses a set of fuzzy ART neural networks as classifiers and Zernike invariant moments as features. The proposed system was trained and tested for the first time using the new database. A height segmentation and recognition accuracy were reported.

Keywords: Arabic database; ground truth information; labelling; Arabic handwriting recognition; character segmentation; Algerian village names; Algeria; offline handwritten words; fuzzy neural networks; fuzzy logic; pattern recognition.

DOI: 10.1504/IJAPR.2013.052342

International Journal of Applied Pattern Recognition, 2013 Vol.1 No.1, pp.81 - 98

Received: 10 Aug 2012
Accepted: 09 Oct 2012

Published online: 31 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article