Abstract: This study describes new preprocessing methods for hand-written Arabic word using Hough Transform and geometrical processing applied on the skeleton chain list, using characteristic points (end points, intersection points and coin points) of the word in order to estimate 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. The results show that these methods are very powerful for most word images on the Algerian cities name database. The result image is useful for the holistic approach and segmentation approach.
Faouzi Bouchareb , Mouldi Bedda and Salim Ouchetati , 2006. New Preprocessing Methods for Hand-Written Arabic Word. Asian Journal of Information Technology, 5: 609-613.