<![CDATA[The ability to read the Qur'an in accordance with the rules of tajwid is a fundamental aspect of Qur'anic learning, particularly in recognizing the rules of Alif Lam Shamsiyyah and Alif Lam Qamariyyah. However, many students still experience difficulties in accurately identifying these two tajwid rules due to the limited availability of interactive learning media and the lack of technology-based automatic detection systems. Recent advances in artificial intelligence, particularly in the fields of computer vision and object detection, offer promising opportunities to support tajwid learning in a more effective and real-time manner. This study aims to develop an automatic detection system for the tajwid rules of Alif Lam Shamsiyyah and Alif Lam Qamariyyah in images of Qur'anic verses from the Uthmani Mushaf using the YOLOv11s model. The research methodology follows the CRISP-DM framework, consisting of six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset comprises 1,400 images collected from a combination of the Indonesian Ministry of Religious Affairs' digital Mushaf and photographs of printed Mushaf copies. The images were subsequently annotated and augmented using Roboflow. The model was trained using Python on the Google Colab platform with an input image size of 640 × 640 pixels and the Adam optimizer. The evaluation results demonstrate that the YOLOv11s model achieved excellent detection performance, with a precision of 98.5%, a recall of 99.0%, and an mAP@50 of 98.9%. The best-performing model was then deployed as a web-based application using the Flask framework to enable automatic and real-time tajwid detection. Based on the findings, the YOLOv11s model is proven to be an effective solution for supporting interactive, adaptive, and accurate computer vision-based tajwid learning]]>
Copyrights © 2026
