Open AccessAn Effective Approach to Offline Arabic Handwriting Recognition
Author(s) -
Jafaar Alabodi,
Xue Li
Publication year - 2013
Publication title -
international journal of artificial intelligence and applications
Language(s) - English
Resource type - Journals
eISSN - 0976-2191
pISSN - 0975-900X
DOI - 10.5121/ijaia.2013.4601
Subject(s) - computer science , arabic , handwriting , speech recognition , artificial intelligence , natural language processing , linguistics , philosophy
Segmentation is the most challenging part of the Arabic handwriting recognition, due to the uniquecharacteristics of Arabic writing that allows the same shape to denote different characters. In this paper,an off-line Arabic handwriting recognition system is proposed. The processing details are presented inthree main stages. Firstly, the image is skeletonized to one pixel thin. Secondly, transfer each diagonallyconnected foreground pixel to the closest horizontal or vertical line. Finally, these orthogonal linesarecoded as vectors of unique integer numbers; each vector represents one letter of the word. In order toevaluate the proposed techniques, the system has been tested on the IFN/ENIT database, and theexperimental results show that our method is superior to those methods currently available