<![CDATA[Tajwid learning faces challenges in visually recognizing recitation rules from Arabic script, thus requiring an interactive and accurate digital medium. This study aims to develop a web-based application to automatically detect seven core tajwid rules using YOLOv8. This research follows a Research and Development approach adopting the ADDIE model, which consists of five systematic stages: analysis, design, development, implementation, and evaluation. The YOLOv8 model was trained using 200 annotated images of Qur’anic verses, with a data split of 70% for training, 20% for validation, and 10% for testing. Data augmentation was applied through rotation, flipping, and brightness adjustment, with training facilitated using Roboflow. Our main finding is an interactive web application capable of automatically detecting seven tajwid rules from Qur’anic verse images. The application allows users to upload images, which are then analyzed and displayed with colored bounding boxes and interactive captions. Testing results showed accurate and responsive detection performance, achieving a mAP@50 of 89.88% with high accuracy across several tajwid classes. These findings highlight the potential of Artificial Intelligence (AI) to support more interactive, independent, and adaptive tajwid learning, while also promoting the digitization of Islamic manuscripts.]]>
Copyrights © 2025
