TY  - JOUR
T1  - Recognition of Similar Shaped Handwritten Arabic Characters Using
Neural Network
AU - A. Al-Jawfi, Rashad 
JO  - International Journal of Soft Computing
VL  - 14
IS  - 1
SP  - 1
EP  - 5
PY  - 2019
DA  - 2001/08/19
SN  - 1816-9503
DO  - ijscomp.2019.1.5
UR  - https://makhillpublications.co/view-article.php?doi=ijscomp.2019.1.5
KW  - Character recognition
KW  -image segmentation
KW  -pattern matching
KW  -smoothing
KW  -handwriting
KW  -extraction
KW  -approaches
AB  - Recognition of Arabic handwriting characters is a difficult task due to similar appearance of some
different characters. However, the selection of the method for feature extraction remains the most important step
for achieving high recognition accuracy. In this study, a novel method is provided to recognize handwritten
Arabic characters based on their features extraction and adaptive smoothing technique. In this study,
combination of two approaches will be introduce, one of them is feature selections methods and the other is
adaptive smoothing technique from smooth shape of character. Combination of both these approaches leads
to the better results.
ER  -