<![CDATA[Addressing the recognized limitation of non-adaptive "one-size-fits-all" experiences in cultural and technical exhibitions, a novel, real-time system is introduced that integrates facial ethnicity classification with the Godot game engine to provide a personalized cultural interactive learning. The core objective was to design and quantitatively assess a performant artifact capable of dynamically classifying users into one of three major Indonesian regional categories (Barat, Tengah, or Timur) and instantly loading the appropriate personalized cultural gaming scenario. The study presents three significant contributions. First, an advanced machine learning model for Indonesian ethnicity categorization was created by utilizing an optimized feature combination of Gray Level Co-occurrence Matrix (GLCM) and Histogram of Oriented Gradients (HOG). The optimal feature set (GLCM+HOG) attained a high Cross-Validation Accuracy 95.82%±1.11%, significantly advancing the technical performance baseline for this domain. Second, a robust, real-time pipeline was successfully demonstrated, connecting the Python-based machine learning backend with the Godot gaming client via an API for immediate content customization. While the backend demonstrates high theoretical efficiency, achieving a throughput of approximately 46 FPS 21.51 ms classification latency), the final integrated system operates at a stable 12.0 FPS interface rate. This performance disparity highlights that integration overhead and feature dimensionality are the primary bottlenecks affecting the responsiveness of the on-demand classification event. Future endeavors will concentrate on enhancing real-time performance by lowering classification latency via feature dimensionality reduction (e.g., Local Binary Pattern variants) and conducting qualitative assessments to gauge user involvement and the transfer of cultural information.]]>
