![](/images/graphics-bg.png)
Recognition of Arabic handwritten characters using residual neural networks
Joint Authors
al-Taani, Ahmad T.
Ahmad, Sadim T.
Source
Jordanian Journal of Computetrs and Information Technology
Issue
Vol. 7, Issue 2 (30 Jun. 2021), pp.192-205, 14 p.
Publisher
Princess Sumaya University for Technology
Publication Date
2021-06-30
Country of Publication
Jordan
No. of Pages
14
Main Subjects
Educational Sciences
Information Technology and Computer Science
Abstract EN
This study proposes the use of Residual Neural Networks (ResNets) to recognize Arabic offline isolated handwritten characters including Arabic digits.
ResNets is a deep learning approach which showed effectiveness in many applications more than conventional machine learning approaches.
the proposed approach consists of three main phases: pre-processing phase, training the ResNet on the training set and testing the trained ResNet on the datasets.
the evaluation of the proposed approach is performed on three available datasets: MADBase, AIA9K and AHCD.
the proposed approach achieved accuracies of 99.8%, 99.05% and 99.55% on these datasets, respectively.
it also achieved a validation accuracy of 98.9% on the constructed dataset based on the three datasets.
American Psychological Association (APA)
al-Taani, Ahmad T.& Ahmad, Sadim T.. 2021. Recognition of Arabic handwritten characters using residual neural networks. Jordanian Journal of Computetrs and Information Technology،Vol. 7, no. 2, pp.192-205.
https://search.emarefa.net/detail/BIM-1415801
Modern Language Association (MLA)
al-Taani, Ahmad T.& Ahmad, Sadim T.. Recognition of Arabic handwritten characters using residual neural networks. Jordanian Journal of Computetrs and Information Technology Vol. 7, no. 2 (Jun. 2021), pp.192-205.
https://search.emarefa.net/detail/BIM-1415801
American Medical Association (AMA)
al-Taani, Ahmad T.& Ahmad, Sadim T.. Recognition of Arabic handwritten characters using residual neural networks. Jordanian Journal of Computetrs and Information Technology. 2021. Vol. 7, no. 2, pp.192-205.
https://search.emarefa.net/detail/BIM-1415801
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 204-205
Record ID
BIM-1415801