Comparative Optimization of Tajwid Detection in Quranic Verses Using Deep Learning

Adinesa Mukharam; Muhammad Zakariyah

doi:10.58526/jsret.v4i4.973

Authors

Adinesa Mukharam Universitas Teknologi Yogyakarta
Muhammad Zakariyah Universitas Teknologi Yogyakarta

DOI:

https://doi.org/10.58526/jsret.v4i4.973

Keywords:

Artificial Intelligence, Computer Vision, Deep Learning, Qur’an, Tajwid Detection

Abstract

This study addresses the challenge of accurate Qur’anic recitation, particularly the rules of nun sakinah and tanwin, which are often difficult for learners to master through traditional instruction. The research aims to develop and evaluate an automated tajwid detection system using a deep learning–based object detection model to assist learners in accurately and interactively recognizing tajwid rules. The method involved dataset preparation from 125 Qur’anic pages, producing 600 annotated instances across five tajwid classes. The dataset was preprocessed and divided into training, validation, and test sets. Model performance was evaluated using precision, recall, and mean Average Precision. The system was deployed in a web-based interface that supports both image upload and real-time camera detection. The results showed an overall accuracy of 94.6%, with a precision of 96.5% and a recall of 90.2%. The findings indicate that the Smart Tajwid system effectively integrates deep learning and educational technology to support Qur’anic learning

Downloads

Download data is not yet available.

References

Tarshany, Y., & Zeki, A. M. (2024). ICT studies for Islamic sciences and the Holy Qur’an: Series. ResearchGate. https://www.researchgate.net/profile/Yasser-Tarshany/publication/380880730_ICT_studies-for-Islamic-Sciences-and-the-Holy-Qur’an_Series_1/links/6652ea990b0d2845745b1560/ICT-studies-for-Islamic-Sciences-and-the-Holy-Qur’an-Series-1.pdf

Engkizar, E., Jaafar, A., & Alias, M. F. B. (2025). Utilisation of artificial intelligence in Quranic learning: Innovation or threat? Journal of Qur’anic Education Research. https://doi.org/10.18860/ijazarabi.v8i1.28804

Fardal, M., & Min, A. (2024). Klasifikasi hukum tajwid mad dalam Surah Al-Fatihah menggunakan algoritma.

Hemmet, A. (2023). Harmonizing artificial intelligence with Islamic values: A thoughtful analysis of religious, social, and economic impacts of technological advancements. Academia.edu. https://www.academia.edu/download/109283598/Article_AI_Islam_Abdullah_Hemmet.pdf

Ariani, S., & Realita, D. (2020). Tajwid rules and phonetic structure of Qur’anic Arabic. Islamic Linguistics Press.

Ellyadi, M. (2022). Deteksi tajwid nun mati pada ayat Al-Qur’an dengan metode convolutional neural network menggunakan model training SSD MobileNet (Skripsi). Universitas Islam Negeri Ar-Raniry.

Prayitna, D. H., et al. (2022). Perancangan prototype deteksi kelengkapan. Jurnal Inovasi Informatika, 7(1), 57–69.

Noor, R., & Ariffin, S. (2020). E-learning approaches for tajweed education. Education and Information Technologies.

Zulkifli, H., & Jamal, R. (2021). Integrating AI and Islamic pedagogy: Challenges and opportunities. Islamic Education Technology Journal.

Rahman, M. T., & Iqbal, N. (2024). AI in religious text digitization: Preservation and interpretation accuracy. Digital Humanities and Religion Review.

Al-Khalifa, H. S. (2018). Ontological representation of tajweed rules in Qur’an digital applications. Journal of Semantic Web Studies.

Kulkarni, N. P., Jolad, B., & Patil, A. G. (2025). DSKN: Deep spiking Kronecker network for leaf type classification and multi-class leaf disease detection in IoT-based sustainable agriculture. Neural Computing and Applications. https://link.springer.com/article/10.1007/s12065-025-01050-w

Alqahtani, M. (2022). YOLOv7 for Arabic calligraphy recognition. Arabian Journal of Computer Vision.

Ahmed, A., & Bashir, U. (2021). Applying YOLO for symbol detection in religious manuscripts. Journal of Visual Computing.

Padilah, A., Nugroho, M., & Rahman, S. (2023). YOLOv8 for nun sakinah detection in Qur’an texts. Journal of Islamic AI Research.

Hamdhana, H., Ellyadi, M., & Fardal, A. (2022). Automated tajweed detection using Euclidean and Bray-Curtis distance methods. Indonesian Journal of Islamic Technology.

Fajar, R., & Nugraha, D. (2023). Hybrid CNN–LSTM for diacritic detection in Qur’an manuscripts. Journal of Deep Learning Applications.

Hamdhana, D., Fadlisyah, F., & Adani, S. (2018). Sistem pendeteksi pola tajwid Al-Qur’an hukum ikhfa syafawi dan idgham mimi pada citra menggunakan metode Euclid distance dan Bray Curtis distance. TECHSI: Jurnal Teknik Informatika, 10(2), 109. https://doi.org/10.29103/techsi.v10i2.886

Padilah, D., Pambudi, A., & Az-Zahra, F. F. (2024). Analisis prediksi tajwid nun mati pada ayat Al-Qur’an. Jurnal …, 8(5), 10190–10196.

Akhtar, A., & Khalid, F. (2022). Arabic OCR and deep learning: A review. International Journal of Arabic Computing.

Nugroho, P. A., Febriana, I., & Arijanto, R. (2020). Implementasi deep learning menggunakan convolutional neural network (CNN) pada ekspresi manusia. Algor, 2(1), 12–21.

Mahmud, I., Ritu, S. A., & Mahmood, Z. Z. (2024). Advancing autonomous navigation: YOLO-based road obstacle detection and segmentation for Bangladeshi environments. https://dspace.bracu.ac.bd/xmlui/handle/10361/24349

Mulyana, D. I., & Rowis, M. A. I. (2022). Optimization of text mining detection of tajweed reading laws using the YOLOv8 method on the Qur’an. Qalamuna: Jurnal Pendidikan, Sosial, dan Agama. https://doi.org/10.37680/qalamuna.v14i2.3866

Jocher, G., & Ultralytics Team. (2023). YOLOv8: Next-generation object detection and segmentation models. https://github.com/ultralytics/ultralytics

Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv. https://arxiv.org/abs/2004.10934

Roboflow Inc. (2023). Roboflow annotate and preprocess toolkit for computer vision. https://roboflow.com

Gupta, C., Gill, N. S., Gulia, P., Kumar, A., & Karamti, H. (2025). An optimized YOLO-NAS based framework for realtime object detection. Scientific Reports. https://doi.org/10.1038/s41598-025-17919-w

Verma, A. (2025). Enhancing web-based object recognition: Employing pretrained models for accurate and efficient visual recognition in real-time scenarios (Master’s thesis). National College of Ireland. https://norma.ncirl.ie/id/eprint/7719

Haq, I., He, L., Li, J., Chen, B., Yang, X., & Li, Y. (2025). Integrated microfluidics and deep learning for detection and interpretation of colon cancer-associated ascitic cells using bright-field microscopy. Physica Scripta. https://iopscience.iop.org/article/10.1088/1402-4896/adedce/meta

Sapkota, R., Raza, S., Shoman, M., & Paudel, A. (2025). Multimodal large language models for image, text, and speech data augmentation: A survey. arXiv. https://arxiv.org/abs/2501.18648

Benkirat, I. (2023). Design and implementation of a real-time object detection and understanding system using deep neural networks to assist the visually impaired (Thesis). University of Guelma. https://dspace.univ-guelma.dz/jspui/handle/123456789/14925