<![CDATA[Conventional mathematics learning at the elementary level often lacks interactivity, leading to low student motivation. This issue hinders the development of foundational analytical skills, despite significant time allocation in the curriculum. This research addresses this pedagogical problem by developing an educational game that replaces traditional input methods with kinesthetic interaction, aiming to directly enhance student engagement. The proposed method is a real-time hand gesture detection system built on a desktop platform. The system utilizes the MediaPipe framework to accurately extract 21 key hand landmarks from a live video feed, which serve as robust features for analysis. These features are then classified using a Random Forest algorithm, chosen for its efficiency and high performance in handling complex data, with an undersampling technique applied to ensure a balanced dataset. The performance evaluation showed that the developed classification model achieved a high accuracy of up to 98% on the test data. The resulting functional prototype allows users to answer addition and subtraction problems intuitively through hand gestures, featuring direct visual feedback and a score-tracking mechanism. This study successfully demonstrates that digital image processing can be effectively leveraged to create an engaging and adaptive mathematics learning experience. This approach not only addresses motivation in mathematics but also demonstrates the potential of gesture-based kinesthetic learning for designing a new class of engaging educational tools across various subjects, highlighting its broader impact on future educational game design.]]>
Copyrights © 2025
