Improved Technique in Arabic Handwriting Recognition
DOI:
https://doi.org/10.58564/IJSER.4.2.2025.316Keywords:
Convolutional Neural Networks (CNN), Classification, Handwritten Text Identification, Feature Extraction, Recognition Challenges, Support Vector Machines (SVM)Abstract
Arabic handwriting recognition has significant applications in fields like postal sorting, handwritten text identification, and cheque processing. The process involves several steps: preprocessing, feature extraction, and classification. Preprocessing enhances image quality through noise removal, normalisation, and binarisation, which are essential for accurate segmentation. Feature extraction captures key information such as stroke direction and spatial relationships, which are crucial for distinguishing between different characters. Hybrid methods, statistical features, and structural features are typical feature extraction strategies. Next, classification methods such as K-nearest neighbour and Support Vector Machines are employed to categorise the extracted features into predefined classes. The effectiveness of Arabic handwriting recognition systems depends heavily on the quality of feature extraction, which directly impacts recognition accuracy. Researchers have explored various techniques, including structural and statistical feature extraction, to optimise these systems. Exceptional accuracy rates are achieved through the utilisation of the proposed SVM linear kernel and KNN classifier with 99.64% and 97%, respectively.
References
S. B. Ahmed, M. I. Razzak, and R. Yusof, Cursive Script Text Recognition in Natural Scene Images. Singapore: Springer Singapore, 2020.
[2] M. Awni, M. I. Khalil, and H. M. Abbas, "Offline Arabic handwritten word recognition: A transfer learning approach," Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 10, pp. 9654-9661, 2022.
[3] M. Salam and A. A. Hassan, "Offline isolated Arabic handwriting character recognition system based on SVM," Int. Arab J. Inf. Technol., vol. 16, no. 3, pp. 467-472, 2019.
[4] A. M. Mutawa, M. Y. Allaho, and M. Al-Hajeri, “Machine Learning Approach for Arabic Handwritten Recognition,” Applied Sciences, vol. 14, no. 19, p. 9020, Oct. 2024.
[5] A. M. Al-Shatnawi, F. Al-Saqqar, and A. Souri, "Arabic handwritten word recognition based on stationary wavelet transform technique using machine learning," Transactions on Asian and Low-Resource Language Information Processing, vol. 21, no. 3, pp. 1-21, 2021.
[6] M. Aouine, Abdeljalil Gattal, Chawki Djeddi, and F. Abbas, “Handwritten digit recognition using a column scheme-based local directional number pattern,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 6, pp. 4157–4167, Sep. 2024.
[7] C. Sharma, S. Sharma, None Sakshi, and H.-Y. Chen, “Advancements in handwritten Devanagari character recognition: a study on transfer learning and VGG16 algorithm,” Deleted Journal, vol. 6, no. 12, Nov. 2024.
[8] S. Aabed and A. Khairaldin, “An End-to-End, Segmentation-Free, Arabic Handwritten Recognition Model on KHATT,” arXiv.org, 2024.
[9] M. N. AlJarrah, M. Z. Mo’ath, and R. Duwairi, "Arabic handwritten characters recognition using convolutional neural network," in 2021 12th International Conference on Information and Communication Systems (ICICS), IEEE, 2021.
[10] Manel Ayadi, Nesrine Masmoudi, Latifa Almuqren, Raneem Oudah Aljohani, and Hadeel Saeed Alshahrani, “Empowering Accessibility in Handwritten Arabic Text Recognition for Visually Impaired Individuals through Optimized Generative Adversarial Network (GAN) model,” Journal of disability research, vol. 4, no. 1, Jan. 2025
[11] H. Al-Yousefi and S. S. Upda, "Recognition of Arabic characters," IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. 08, pp. 853-857, 1992.
[12] F. Salameh, "“Young Phoenicians” and the quest for a Lebanese language: between Lebanonism, Phoenicianism, and Arabism," in Arabic and Its Alternatives, Brill, 2020, pp. 111-129.
[13] Y. Hamdi, H. Boubaker, and A. M. Alimi, "Online Arabic handwriting recognition using graphemes segmentation and deep learning recurrent neural networks," in Enabling Machine Learning Applications in Data Science: Proceedings of Arab Conference for Emerging Technologies 2020, Singapore: Springer Singapore, 2021.
[14] Y. B. Hamdan and A. Sathesh, "Construction of statistical SVM based recognition model for handwritten character recognition," Journal of Information Technology, vol. 3, no. 2, pp. 92-107, 2021.
[15] W. Alomoush et al., "Fully automatic grayscale image segmentation based fuzzy C-means with firefly mate algorithm," Journal of Ambient Intelligence and Humanized Computing, vol. 13, no. 9, pp. 4519-4541, 2022.
[16] W.-C. Cheng et al., "Image haze removal using dark channel prior technology with adaptive mask size," Sensors & Materials, vol. 32, 2020.
[17] R. A. Lotufo et al., "Morphological image processing," in Microscope Image Processing, Academic Press, 2023, pp. 75-117.
[18] S. Djaghbellou, A. Attia, and A. Bouziane, "A survey on text-line segmentation process in historical Arab manuscripts," IAM, 2023.
[19] S. Hamida et al., "Cursive Arabic handwritten word recognition system using majority voting and k-NN for feature descriptor selection," Multimedia Tools and Applications, vol. 82, no. 26, pp. 40657-40681, 2023.
[20] H. M. Balaha, H. A. Ali, and M. Badawy, "Automatic recognition of handwritten Arabic characters: A comprehensive review," Neural Computing and Applications, vol. 33, pp. 3011-3034, 2021.
[21] A. Y. Muaad et al., "Arabic document classification: Performance investigation of preprocessing and representation techniques," Mathematical Problems in Engineering, vol. 2022, no. 1, p. 3720358, 2022.
[22] S. K. Jemni, Y. Kessentini, and S. Kanoun, "Improving recurrent neural networks for offline Arabic handwriting recognition by combining different language models," International Journal of Pattern Recognition and Artificial Intelligence, vol. 34, no. 12, p. 2052007, 2020.
[23] J. Memon et al., "Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR)," IEEE Access, vol. 8, pp. 142642-142668, 2020.
[24] S. B. Ahmed, M. I. Razzak, and R. Yusof, Cursive Script Text Recognition in Natural Scene Images. Singapore: Springer Singapore, 2020.
[25] A. Ganguly, R. Mitra, and J. Zhou, "Infinite-dimensional optimization and Bayesian nonparametric learning of stochastic differential equations," Journal of Machine Learning Research, vol. 24, no. 159, pp. 1-39, 2023.
[26] J. W. Shavlik and T. G. Dietterich, Eds., Readings in Machine Learning. Morgan Kaufmann, 1990.
[27] N. N. Abboud, "A mixed finite element formulation for the transient and harmonic exterior fluid-structure interaction problem," Stanford University, 1990.
[28] M. Steinbach and P.-N. Tan, "kNN: k-nearest neighbors," in The Top Ten Algorithms in Data Mining. Chapman and Hall/CRC, pp. 165-176, 2009.
[29] H. waleed Hamza, A. A. Al-Hamadani, “A Review on Artificial Intelligence methods and Signal Processing for EEG-Based lie and Truth Identification,” Al-Iraqia Journal of Scientific Engineering Research, vol. 3, no. 2, Jun. 2024
[30] S. Mohammed Tariq, “Spatial Analysis of Local Statistics for Handwritten Signature Recognition”, Al-Iraqia Journal of Scientific Engineering Research, vol. 3, no. 2, pp. 10–20, Jun. 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ammar A. Al-Hamadani, Maad Kamal Al-Anni, Gamil R. S. Qaid, Najran Nasser Hamood
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
