Virtual Booth

Monitoring student engagement in online higher education remains a critical challenge, as conventional attendance and participation metrics fail to capture genuine attentiveness. Obserixis AI: Post-Class Engagement Intelligence System addresses this gap by leveraging AI-driven facial analytics to quantify post-class engagement with precision and objectivity. Developed using Python, OpenCV’s Haarcascade classifier, and MediaPipe’s 468-point Face Mesh model, Obserixis AI analyzes gaze direction, facial expressions, and micro-behavioral indicators to evaluate both individual and collective engagement levels. The system generates actionable analytics that enable educators to identify disengaged learners, refine instructional strategies, and strengthen Continuous Quality Improvement (CQI) initiatives. Aligned with Outcome-Based Education (OBE) frameworks, Obserixis AI provides data-driven insights that support evidence-informed pedagogical decisions and improved learning outcomes. Its scalable architecture allows seamless integration into existing online teaching ecosystems, transforming recorded lectures into meaningful engagement intelligence. Obserixis AI demonstrates how artificial intelligence can elevate digital education from passive content delivery to measurable, adaptive, and student-centered learning experiences.