LEADER |
01819nam a22002297a 4500 |
001 |
0008904 |
041 |
|
|
|a eng
|
044 |
|
|
|b المغرب
|
100 |
|
|
|9 24331
|a Boumaza, Kamel
|e Author
|
245 |
|
|
|a Using Neural Networks to Desciminate between Arabic and Latin Writing
|
260 |
|
|
|b معهد الدراسات والأبحاث للتعريب
|c 2007
|g يناير
|
300 |
|
|
|a 106 - 118
|
336 |
|
|
|a بحوث المؤتمرات
|b Conference Proceedings
|
500 |
|
|
|a المقال باللغة الانجليزية
|
520 |
|
|
|b In this paper, we propose a method of an Arabic and Latin discrimination writings, based on morphological, geometrical and statistical analysis. We focused on feature extractions in order to curry out a system able to differentiate between printed or handwritten Arabic and Latin scripts. First, an image acquisition is made by means of a scanner, and then come some pre-treatment steps. After that, we extract the different features constituting an input vector of multi¬layer perceptron (MLP) with back-propagation algorithm. Finally and thanks to the network outputs we have been able to undertake a discrimination of each script (Printed or handwritten). The aim of our work is to constitute a postal sorting system in French-Arabic sneaking countries.
|
653 |
|
|
|a استخدام الشبكات العصبية
|a التمييز الكتابي
|a اللغة العربية
|a اللغة اللاتينية
|
700 |
|
|
|9 47282
|a Sellami, Mokhtar
|e Co-Author
|
773 |
|
|
|c 023
|l 000
|o 6868
|s وقائع الندوة الدولية : المعالجة الآلية للغة العربية
|v 000
|d الرباط
|i معهد الدراسات والأبحاث للتعريب بالرباط - جامعة محمد الخامس
|
856 |
|
|
|u 6868-000-000-023.pdf
|
930 |
|
|
|d y
|p y
|
995 |
|
|
|a AraBase
|
999 |
|
|
|c 594240
|d 594240
|