A Deep CNN-BiLSTM Framework for Arabic Handwritten Text Recognition
Received: 21 December 2025 | Revised: 2 February 2026 | Accepted: 13 February 2026 | Online: 5 March 2026
Corresponding author: Muhammad Ramzan
Abstract
Text recognition is one of the most essential aspects of pattern recognition and Natural Language Processing (NLP). Although there is much research on handwritten text recognition, Arabic text recognition is a challenging task not only due to linguistic diversity and complexity, but also due to handwritten text variations, including shape, skew, cursive style, fonts, and formats. The KHATT dataset includes a wide variety of handwritten text from people across different countries. This study presents a framework that combines Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNN). The input data was preprocessed by segmenting it into lines and applying adaptive thresholding for binarization. Data augmentation was also performed to improve model training. Α Character Error Rate (CER) of 13% was obtained, demonstrating that the proposed system outperformed state-of-the-art techniques.
Keywords:
Arabic handwritten text recognition, bidirectional long short-term memory, connectionist temporal classification, optical character recognition, CNNDownloads
References
A. Shetty and S. Sharma, ''Ensemble deep learning model for optical character recognition,'' Multimedia Tools and Applications, vol. 83, no. 4, pp. 11411–11431, Jan. 2024.
M. El Khayati, I. Kich, and Y. Taouil, ''CNN-based Methods for Offline Arabic Handwriting Recognition: A Review,'' Neural Processing Letters, vol. 56, no. 2, Mar. 2024, Art. no. 115.
S. Amar''A Detailed study and recent research on OCR,'' Vol. 19 No. 2 International Journal of Computer Science and Information Security (IJCSIS), vol. 19 no. 2, Jan. 2021.
N. Sahu and M. Sonkusare, "A Study on Optical Character Recognition Techniques," International Journal of Computational Science, Information Technology and Control Engineering, vol. 4, no. 1, pp. 01–15, Jan. 2017.
K. Hamad and M. Kaya, ''A Detailed Analysis of Optical Character Recognition Technology,'' International Journal of Applied Mathematics Electronics and Computers, no. Special Issue-1, pp. 244–249, Dec. 2016.
M. G. Mahdi, A. Sleem, and I. El-henawy, ''Deep Learning Algorithms for Arabic Optical Character Recognition: A Survey,'' Multicriteria Algorithms with Applications, vol. 2, pp. 65–79, Jan. 2024.
S. A. Mahmoud et al., ''KHATT: An open Arabic offline handwritten text database,'' Pattern Recognition, vol. 47, no. 3, pp. 1096–1112, Mar. 2014.
M. Elsayed, A. Alnaggar, M. Abdeen, A. Wahdan, and W. Gomaa, "Arabic Handwritten Text Recognition using Advanced CNN-RNN Architecture," in 6th IAPR International Workshop on Document Analysis Systems (DAS) ICDAR, 2023.
S. Momeni and B. BabaAli, ''A transformer-based approach for Arabic offline handwritten text recognition,'' Signal, Image and Video Processing, vol. 18, no. 4, pp. 3053–3062, June 2024.
S. Aabed and A. Khairaldin, ''An End-to-End, Segmentation-Free, Arabic Handwritten Recognition Model on KHATT.'' arXiv, June 21, 2024.
A. M. Mutawa, M. Y. Allaho, and M. Al-Hajeri, ''Machine Learning Approach for Arabic Handwritten Recognition,'' Applied Sciences, vol. 14, no. 19, Oct. 2024.
R. Ahmad, S. Naz, M. Afzal, S. Rashid, M. Liwicki, and A. Dengel, ''A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT,'' The International Arab Journal of Information Technology, vol. 17, no. 3, pp. 299–305, May 2020.
F. Alwajih, E. Badr, and S. Abdou, ''Transformer-based models for Arabic online handwriting recognition, International Journal of Advanced Computer Science and Applications, vol. 13, no. 5, pp. 6, 2022.
L. Berriche, A. Alqahtani, and S. RekikR, ''Hybrid Arabic handwritten character segmentation using CNN and graph theory algorithm,'' Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 1, Jan. 2024, Art. no. 101872.
B. Kada, A. Mohammed, and B. Abdelmajid, ''An Optimized Approach for Handwritten Arabic Character Recognition based on the SVM Classifier,'' Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 22232–22238, Apr. 2025.
S. A. Mahmoud et al., ''KHATT: Arabic Offline Handwritten Text Database,'' in 2012 International Conference on Frontiers in Handwriting Recognition, Sept. 2012, pp. 449–454.
Downloads
How to Cite
License
Copyright (c) 2026 Muhammad Ramzan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
