The Indonesian Sign Language System (SIBI) is the officially recognized communication medium for deaf communities in Indonesia, yet its limited public use continues to create barriers in education, healthcare, and public services. Automatic sign language recognition powered by artificial intelligence provides a promising pathway to reduce these inequities. This study presents a comprehensive comparative evaluation of YOLOv8 segmentation variants for SIBI recognition, aiming to identify models that stabilize accuracy and efficiency for real-time deployment. A mono-background dataset of SIBI alphabet gestures was annotated using instance segmentation, and five YOLOv8-seg models (n, s, m, l, x) were trained and tested across multiple data-split scenarios. Performance was assessed through precision, recall, F1-score, mAP50, mAP50–95, and inference time. Results show that YOLOv8m-seg consistently achieved the best trade-off (F1-score 0.972; mAP50 0.982), while YOLOv8n-seg delivered the fastest inference speed (5.163 ms), making it suitable for resource-constrained devices. Visualization further demonstrated the models’ ability to capture hand contours and distinguish gestures accurately. Beyond technical benchmarking, this research highlights the potential of YOLOv8-based SIBI recognition as an inclusive assistive technology for bridging communication gaps in schools and clinics where interpreters are often unavailable. It also identifies governance challenges, including privacy protection, misclassification risks, and equitable access, which must be addressed for actual adoption. The findings, therefore, provide not only a contribution to computer vision research but also practical guidance for policymakers and service providers, positioning SIBI recognition systems as socially embedded technologies aligned with the goals of disability inclusion and sustainable development.
Azizah et al. (Wed,) studied this question.