Proceedings of the 4th International Conference on Informatics, Technology and Engineering 2023 (InCITE 2023)

Arabic Letter Classification Using Convolutional Neural Networks for Learning to Write Quran

Authors
Mohammad Farid Naufal1, *, Muhammad Zain Fawwaz Nuruddin Siswantoro2, Andre1
1Department of Informatics Engineering, Faculty of Engineering, University of Surabaya, Surabaya, Indonesia
2Department of Informatics, Faculty of Intelligent Electrical and Informatics Technology, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
*Corresponding author. Email: faridnaufal@staff.ubaya.ac.id
Corresponding Author
Mohammad Farid Naufal
Available Online 19 November 2023.
DOI
10.2991/978-94-6463-288-0_47How to use a DOI?
Keywords
Arabic letter classification; Convolutional Neural Networks; Quranic script; Arabic language learning; educational technology
Abstract

Learning to write the Arabic language, particularly the Arabic letters used in the Quran, is essential for individuals who aim to understand and recite the holy book accurately. In this research, we propose a classification method utilizing Convolutional Neural Networks (CNNs) with MobileNet architecture to automatically identify and classify Arabic letters. The CNN model is trained on a large dataset of labeled Arabic letter images, encompassing various styles and variations commonly found in the Quranic script. The dataset is carefully curated and annotated, incorporating a wide range of Arabic letters with different diacritics and ligatures. The significance of this research lies in its potential to support educational initiatives aimed at teaching Arabic and Quranic studies. The proposed CNN-based Arabic letter classification system can serve as an interactive learning tool, assisting individuals in recognizing and memorizing Arabic letters, thereby facilitating the process of writing the Quran. Additionally, the system can be integrated into mobile applications, making it accessible to a broader audience. The experimental results demonstrate the effectiveness and efficiency of the proposed CNN model for Arabic letter classification, validating its potential to contribute to the field of Arabic language learning. The trained CNN demonstrates remarkable performance in accurately classifying Arabic letters, achieving high accuracy rates of 94% for classifying Arabic letters and 98.43% for classifying harakat.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the 4th International Conference on Informatics, Technology and Engineering 2023 (InCITE 2023)
Series
Atlantis Highlights in Engineering
Publication Date
19 November 2023
ISBN
978-94-6463-288-0
ISSN
2589-4943
DOI
10.2991/978-94-6463-288-0_47How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Mohammad Farid Naufal
AU  - Muhammad Zain Fawwaz Nuruddin Siswantoro
AU  - Andre
PY  - 2023
DA  - 2023/11/19
TI  - Arabic Letter Classification Using Convolutional Neural Networks for Learning to Write Quran
BT  - Proceedings of the 4th International Conference on Informatics, Technology and Engineering 2023 (InCITE 2023)
PB  - Atlantis Press
SP  - 573
EP  - 583
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-288-0_47
DO  - 10.2991/978-94-6463-288-0_47
ID  - Naufal2023
ER  -