Attention Enhanced Convolutional Neural Networks for Arabic Calligraphy Recognition
DOI:
https://doi.org/10.33050/g9wzdk67Kata Kunci:
Arabic Calligraphy, Attention Mechanism, CBAM, CNN, OCRAbstrak
Arabic calligraphy recognition remains a challenging task in computer vision due to the cursive nature of Arabic characters, complex ligatures, diacritics, and diverse artistic writing styles. These characteristics create difficulties for automatic classification systems, particularly in distinguishing visually similar calligraphy patterns. Recent advances in deep learning, especially Convolutional Neural Networks (CNN) and attention mechanisms, provide opportunities to improve feature representation for complex visual recognition tasks. This study aims to develop an Arabic calligraphy recognition model by integrating CNN with the Convolutional Block Attention Module (CBAM) to improve the classification performance of three Arabic calligraphy styles: Naskhi, Riq’ah, and Diwani. The proposed approach utilizes a dataset consisting of 946 Arabic calligraphy images. The images undergo preprocessing, normalization, and augmentation before being processed using CNN for hierarchical feature extraction. CBAM is then applied to enhance feature representation through channel attention and spatial attention mechanisms. The proposed model is evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results demonstrate that the CNN-CBAM model achieves a validation accuracy of 87.37%, outperforming the baseline CNN model with 58.42%. The proposed model also obtains recall values of 100.00% for Riq’ah, 95.31% for Diwani, and 68.18% for Naskhi. The integration of CNN and CBAM effectively improves Arabic calligraphy classification by enhancing discriminative feature learning. The pro- posed approach provides potential support for digital preservation, automated indexing, and intelligent management of Arabic calligraphy collections.
Referensi
[1] S. Alghyaline, “Arabic optical character recognition: A review,” Computer Modeling in Engineering & Sciences, vol. 135, no. 3, pp. 1825–1861, 2023. [Online]. Available: https://doi.org/10.32604/cmes.2022.024555
[2] M. Cleti, “Attention mechanisms in deep learning: A comprehensive survey from foundations to modern applications,” Tech. Rep., 2025. [Online]. Available: https://doi.org/10.13140/RG.2.2.18159.29605
[3] A. A. Zainuddin, R. M. Nor, D. Handayani, M. I. M. Tamrin, K. Subramaniam, and S. F. N. Sadikan, “Smart attendance in classroom (cobot): Iot and facial recognition for educational and entrepreneurialimpact,” Aptisi Transactions on Technopreneurship (ATT), vol. 6, no. 3, pp. 608–622, 2024.
[4] M.-H. Guo et al., “Attention mechanisms in computer vision: A survey,” Computational Visual Media, vol. 8, no. 3, pp. 331–368, Sep. 2022. [Online]. Available: https://doi.org/10.1007/s41095-022-0271-y
[5] K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y. Tang, A. Xiao, C. Xu, Y. Xu, Z. Yang, Y. Zhang, and D. Tao, “A survey on vision transformer,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 87–110, Jan. 2023. [Online]. Available:https://doi.org/10.1109/TPAMI.2022.3152247
[6] M. S. Kasem, M. Mahmoud, and H.-S. Kang, “Advancements and challenges in arabic optical character recognition: A comprehensive survey,” 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2312.11812
[7] Y. Kristiana, V. A. H. Goeltom, and T. C. Nathalia, “Ai-driven pos, adaptable workload, and service culture influence on frontline employee performance,” Aptisi Transactions on Technopreneurship (ATT), vol. 7, no. 1, pp. 217–227, 2025.
[8] H. Lamtougui, H. El Moubtahij, H. Fouadi, and K. Satori, “An efficient hybrid model for arabic text recognition,” Computers, Materials & Continua, vol. 74, no. 2, pp. 2871–2888, 2023. [Online]. Available: https://doi.org/10.32604/cmc.2023.032550
[9] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: Analysis, applications, and prospects,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33,no. 12, pp. 6999–7019, Dec. 2022. [Online]. Available: https://doi.org/10.1109/TNNLS.2021.3084827
[10] Z. Lv, K. Chen, T. Zhang, J. Zhao, and W. Wang, “Multi-feature generation network-based imputation method for industrial data with high missing rate,” Expert Systems with Applications, vol. 227, p.120229, Oct. 2023. [Online]. Available: https://doi.org/10.1016/j.eswa.2023.120229
[11] E. Susetyono, D. S. Priyarsono, A. Sukmawati, and P. Nurhayati, “Improving risk management maturity in ultra micro soe holding companies,” Aptisi Transactions on Technopreneurship (ATT), vol. 8, no. 1, pp. 310–324, 2026.
[12] S. M¨unster et al., “Artificial intelligence for digital heritage innovation: Setting up a R&D agenda for europe,” Heritage, vol. 7, no. 2, pp. 794–816, Feb. 2024. [Online]. Available:https://doi.org/10.3390/heritage7020038
[13] V. Poulopoulos and M. Wallace, “Digital technologies and the role of data in cultural heritage: The past, the present, and the future,” Big Data and Cognitive Computing, vol. 6, no. 3, p. 73, Jul. 2022 [Online]. Available: https://doi.org/10.3390/bdcc6030073
[14] S. O. Salih and K. Jacksi, “KSTRV1: A scene text recognition dataset for central kurdish in (arabic-based) script,” Data in Brief, vol. 60, p. 111648, Jun. 2025. [Online]. Available:https://doi.org/10.1016/j.dib.2025.111648
[15] I. R. Maulana, U. Rahardja, N. Azizah, M. Rakhmansyah, and M. A. Komara, “Leveraging ipfs to build secure and decentralized websites in the web 3.0 era,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 7, no. 1, pp. 1–12, 2025.
[16] T. B. A. Gader and A. K. Echi, “Attention-based deep learning model for arabic handwritten text recognition,” Machine Graphics & Vision, vol. 31, no. 1/4, pp. 49–73, 2022.
[17] P. A. Suraya, T. Ramadhan, N. Lutfiani, A. Khoirunisa, and U. Rahardja, “Blockchain, information and speculation calculations in indonesia: Recent work,” in 2022 10th International Conference on Cyber and IT Service Management (CITSM). IEEE, 2022, pp. 1–8.
[18] E. T. Attar, “Deep convolutional neural network for isolated arabic handwritten character recognition:design, evaluation, and comparative study,” Scientific Reports, vol. 15, no. 1, p. 42467, 2025.
[19] S. L. Sitorus, R. T. H. Safariningsih, A. H. A. N. Karsa, M. A. Komara, and R. Evans, “Optimizing smart contracts and blockchain for sustainable digital fashionpreneurship,” Blockchain Frontier Technology,vol. 5, no. 1, pp. 37–48, 2025.
[20] K. M. Nahar, I. Alsmadi, R. E. Al Mamlook, A. Nasayreh, H. Gharaibeh, A. S. Almuflih, and F. Alasim, “Recognition of arabic air-written letters: machine learning, convolutional neural networks, and opticalcharacter recognition (ocr) techniques,” Sensors, vol. 23, no. 23, p. 9475, 2023.
[21] A. A. H. Al-Radaideh, M. S. bin Mohd Rahim, W. Ghaban, M. Bsoul, S. Kamal, and N. Abbas, “Arabic words extraction and character recognition from picturesque image macros with enhanced vgg-16 based model functionality using neural networks.” KSII Transactions on Internet & Information Systems, vol. 17, no. 7, p. 1807, 2023.
[22] M. Elkhayati, Y. Elkettani, and M. Mourchid, “Segmentation of handwritten arabic graphemes using a directed convolutional neural network and mathematical morphology operations,” Pattern Recognition, vol. 122, p. 108288, 2022.
[23] L. Philip, T. Pradiani et al., “Influence brand experience, viral marketing and brand image to brand loyalty to service users streaming spotify in indonesia,” ADI Journal on Recent Innovation (AJRI), vol. 5, no. 2, pp. 127–135, 2024.
[24] T. B. Aicha and A. K. Echi, “Attention-based cnn-convlstm for handwritten arabic word extraction,” ELCVIA: electronic letters on computer vision and image analysis, vol. 21, no. 1, pp. 121–129, 2022.
[25] K. Miloud, M. L. Abdelmounaim, B. Mohammed, and B. R. Ilyas, “Advancing ancient arabic manuscript restoration with optimized deep learning and image enhancement techniques,” Traitement du Signal, vol. 41, no. 4, p. 2203, 2024.
[26] S. Rahayu, N. Septiani, R. Z. Ikhsan, Y. M. Kareem, U. Rahardja et al., “Revolutionizing renewable energy systems throughadvanced machine learning integration approaches,” Journal of Computer Science and Technology Application, vol. 2, no. 2, pp. 23–34, 2025.
[27] S. S. Qasim and S. H. Oleiwi, “Advancing arabic handwritten digit recognition with ai-enhanced neural network architectures,” Babylonian Journal of Artificial Intelligence, vol. 2024, pp. 146–157, 2024.
[28] S. A. Alsuhibany and T. Alwehaid, “Security and usability evaluation of handwritten arabic captcha systems based on saudi calligraphic fonts,” Scientific Reports, 2026.
[29] C. Salhi, A. El Allati, and M. Ben Ahmed, “Exploring classical and quantum-inspired approaches for arabic handwritten text recognition: A comprehensive and detailed review,” in International Conferenceon Digital Age & Technological Advances for Sustainable Development. Springer, 2025, pp. 64–76.
[30] F. Haque, A. S. M. Miah, M. Al-Hasan, S. T. Mou, M. A. Rahim, and J. Shin, “Multichannel attention networks with ensembled transfer learning to recognize bangla handwritten character,” in Data DrivenApplications for Industry 4.0 and Beyond. Chapman and Hall/CRC, 2025, pp. 172–186.
[31] K. Mirdad, O. P. M. Daeli, N. Septiani, A. Ekawati, U. Rusilowati et al., “Optimizing student engagement and performance usingai-enabled educational tools,” Journal of Computer Science and Technology Application, vol. 1, no. 1, pp. 53–60, 2024.
[32] S. Saber and M. G. Mahdi, “Urdu handwriting recognition with deep learning: Current methods and future prospects,” International Journal of Computers and Informatics (Zagazig University), vol. 3, pp.32–43, 2024.
[33] M. Salaheldin Kasem, M. Mahmoud, and H.-S. Kang, “Advancements and challenges in arabic optical character recognition: A comprehensive survey,” ACM Computing Surveys, vol. 58, no. 4, pp. 1–37, 2025.
[34] M. Ayadi, N. Masmoudi, L. Almuqren, R. O. Aljohani, and H. S. 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, p. 20240110, 2025.
[35] B. A. Tuama and F. Mohamed, “A systematic literature review of deep learning methods for handwritten text recognition in historical arabic manuscripts,” Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25 772–25 782, 2025.
[36] A. A. AGUNG, “Implementasi kegiatan ekstrakurikuler kaligrafi dalam mengembangkan kecerdasan visual spasial peserta didik di ma diniyyah putri lampung,” Ph.D. dissertation, UIN RADEN INTAN LAMPUNG, 2026.
[37] A. A. Chandio, M. Asikuzzaman, M. R. Pickering, and M. Leghari, “Cursive text recognition in natural scene images using deep convolutional recurrent neural network,” IEEE Access, vol. 10, pp. 10 062–10 078, 2022.
[38] Z. A. Umar and M. Yunus, “Optimalisasi teknologi ocr dalam digitalisasi manuskrip hadis: Studi akurasi dan tantangan linguistik arab klasik,” Hamidah: Jurnal Ilmu Hadis, vol. 1, no. 1, pp. 43–54, 2025.
[39] A. Waly, B. Tarek, A. Feteha, R. Yehia, G. Amr, W. Gomaa, and A. Fares, “Invizo: Arabic handwrittendocument optical character recognition solution,” arXiv preprint arXiv:2502.05277, 2025.
[40] J. Wang, X. Liao, Y. Che, P. Wang, Y. Zhang, F. Wang, F. Marias, and H. Rong, “Lstm-cnn-cbam-based prediction of nox emissions with zonal control strategies for flexible peak-load nox reduction in cfb coalfired units,” Journal of Cleaner Production, vol. 545, p. 147705, 2026.
[41] Z. Qin, L. Xu, C. Chen, Y. Qi, Y. Li, and Y. Li, “Cnn-cbam prediction model for moisture content determination of raw materials for wood-based panels based on near-infrared spectroscopy,” Analytical Methods, vol. 18, no. 3, pp. 688–699, 2026.
[42] S. N. A. Norhairi, A. S. A. Nasir, H. B. Affandy, and F. Abdullah, “Hybrid cnn-cbam architecture for facial expression recognition across multiple benchmark datasets,” in 2026 2nd International Conference on Electrical, Robotics and Intelligent Systems (ELECRIS). IEEE, 2026, pp. 450–455.
[43] A. S. Bist, B. Rawat, U. Rahardja, M. Hardini, and M. Kamal, “Unveiling ethical challenges and malpractice in academic research and integrity,” in 2024 3rd International Conference on Creative Communication and Innovative Technology (ICCIT). IEEE, 2024, pp. 1–6.
[44] X. Chen, “Design of a fruit sorting system based on deep learning models optimized by cbam attention mechanism and its simulation verification in coppeliasim,” in 2025 5th International Conference onElectronic Information Engineering and Computer Science (EIECS). IEEE, 2025, pp. 967–972.
[45] X. Xu, J. Sun, and Z. Li, “Research on writer identification based on attention mechanism,” in Sixteenth International Conference on Graphics and Image Processing (ICGIP 2024), vol. 13539. SPIE, 2025, pp. 322–329.
[46] M. Nurkanti, U. Rahardja, M. Lubis, and A. Shukri, “Deep learning-based biology learning with ethnope dagogy and local wisdom to support sustainable development goals,” Jurnal Pendidikan IPA Indonesia, vol. 15, no. 1, pp. 103–111, 2026.
[47] R. Alabdan, M. A. AlAqil, E. M. Alanazi, and A. S. Zamani, “Enhance real-time activity recognition of disabled individuals using hybridisation of convolutional neural network with attention mechanism,”Signal, Image and Video Processing, vol. 19, no. 14, p. 1268, 2025.
[48] OECD, Enhanced Monitoring Report on the Implementation of the Standard on Transparency and Exchange of Information on Request 2025. Paris: OECD Publishing, 2025. [Online]. Available:https://doi.org/10.1787/4db1a02b-en
[49] M. K. Sastry and S. Aparna, “Developing adaptive yolov5-based telugu handwritten character segmentation and classification framework using enhanced chef-based optimization algorithm and deep learning networks,” Computers and Electrical Engineering, vol. 126, p. 110533, 2025.
[50] K. Khoirudin, S. Y. J. Prasetyo, S. Wijono, E. Maria, and U. Rahardja, “Transfer learning in data-scarce agricultural yield forecasting: A bibliometric and systematic literature review,” in 2nd International Conference on Social Environment Diversity (ICOSEND 2025). Atlantis Press, 2026, pp. 467–477.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Indra Riyanto, Muhamad Rido, Marta Rodriguez

Artikel ini berlisensi Creative Commons Attribution 4.0 International License.



