<![CDATA[Modern gesture recognition systems for sign language face challenges in balancing computational efficiency and detection accuracy in complex and dynamic environments. To address this, this study proposes a SIBI alphabet recognition framework based on YOLOv11, optimized for real-time applications. The model architecture integrates a modified, efficient YOLOv11 backbone to enable accurate hand gesture feature extraction with minimal latency. A custom SIBI dataset comprising alphabet signs and essential vocabulary is used to train the model, supported by data augmentation techniques that enhance robustness against variations in position, lighting, and background. Experimental results demonstrate that the model achieves a high detection accuracy with an mAP50 of 97%, while significantly reducing computational complexity. These findings present a meaningful scientific contribution by showcasing how a lightweight yet highly accurate deep learning model can be effectively applied to sign language recognition, particularly for SIBI in the Indonesian context. From a practical standpoint, this framework offers a real-time gesture detection solution that is suitable for deployment on resource-constrained devices, making it accessible for mobile or embedded systems. The system can replace or complement traditional communication aids, especially in inclusive education, public services, and healthcare. Furthermore, the proposed method can be adapted for gesture-based interaction in other domains such as athletic training, physical education, and app-based fitness programs where accurate and real-time motion recognition is essential.]]>
Copyrights © 2025
