Title :
Preprocessing Methods for Hand-written Arabic Words Recognition
Author :
Faouzi, Bouchareb ; Mouldi, BEDDA
Author_Institution :
Univ. de Skikda
Abstract :
This paper describes new schemes of preprocessing for hand-written Arabic word using Hough transform and geometrical processing applied on the chain code of skeleton of the word in order to determine and correct a baseline and slant of the word. We use these algorithms in order to obtain an aligned word which can be well segmented and recognized
Keywords :
Hough transforms; handwritten character recognition; Hough transform; chain code; geometrical processing; hand-written Arabic words recognition; Character recognition; Digital images; Equations; Histograms; Image analysis; Image converters; Natural languages; Optical character recognition software; Shape; Skeleton;
Conference_Titel :
Information and Communication Technologies, 2006. ICTTA '06. 2nd
Conference_Location :
Damascus
Print_ISBN :
0-7803-9521-2
DOI :
10.1109/ICTTA.2006.1684661