Integrating Computer Vision and Large Language Models to Revitalize Dakon as Intangible Cultural Heritage

Abstract Traditional board games are increasingly digitized, yet many digital adaptations reduce embodied interaction and weaken cultural meaning. This study proposes a multimodal framework to revitalize Dakon as an intangible cultural heritage practice by integrating gesture-based computer vision and large language models. The system combines MediaPipe hand landmark detection, a Support Vector Machine classifier for gesture recognition, a deterministic Dakon game engine, and event-driven generative dialogue using Gemini 3 Flash. Experimental results show perfect precision across active gesture classes, with recall values ranging from 0.72 to 0.77, indicating that performance limitations primarily stem from hand detection robustness rather than classification accuracy. User experience evaluation involving twenty participants demonstrates high levels of engagement, perceived authenticity, clarity, and responsiveness. In addition, linguistically informed evaluation of 120 LLM-generated responses by expert evaluators reveals strong performance in cultural relevance, contextual accuracy, and motivational quality. The findings highlight that separating deterministic game logic from generative AI preserves gameplay authenticity while enabling contextual cultural interpretation. This study contributes a heritage-centered design principle in which generative AI functions as an interpretative layer rather than a rule-modifying agent. The proposed approach extends digital cultural preservation beyond static digitization toward interactive, embodied, and participatory experiences.