<![CDATA[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]]>
Copyrights © 2025
