عنوان المقالة:نظام التعرف على الحروف العربية باستخدام طرق استخراج الميزات المتعددة ACRS: Arabic Character Recognition System Based on Multi Features Extraction Methods
Mustafa S.Kadhm, Asst. Prof. Dr. Alia Karim Abdul Hassan
الملخص العربي
this paper proposed a new architecture for Arabic Character Recognition System Based on Multi Features Extraction Methods
and SVM Classifier (ACRS). An Arabic handwriting dataset proposed as well for training and testing the proposed system. Although half of
the dataset used for training the SVM and the second half used for testing, the system achieved high performance with less training data.
Besides, the system achieved best recognition accuracy 99.64% based on several feature extraction methods and SVM c
تاريخ النشر
01/10/2015
الناشر
International Journal of Scientific and Engineering Research