• RAKESH KUMAR
• KHADAR BASHA
• R.USHARANI

Classroom monitoring is essential for fostering an effective learning environment, yet manual supervision is often resource-intensive and may overlook subtle indicators of student engagement and behavior. This paper proposes an automated solution using the Florence 2 model, a state-of-the-art vision transformer for image and video analysis. The system addresses challenges in monitoring student activities, such as attentiveness and participation, by leveraging Florence 2’s advanced image recognition capabilities to track faces, movements, and gestures in real-time.By capturing classroom video feeds and applying pre-processing techniques, the model classifies behaviors and generates actionable insights for educators, enabling timely interventions. Implemented with Python libraries like OpenCV and TensorFlow, the solution demonstrates a 85% accuracy rate in behavior classification, a 25% increase in student engagement, and a 15% reduction in disruptive incidents. This scalable system not only enhances discipline but also empowers educators to tailor their teaching strategies, ultimately improving student outcomes.

computer vision , vision transformers , florence-2, Student Engagement Analysis, Behavior Classification

"IMAGE INTERPRETATION ANALYSIS UTILIZING THE FLORENCE 2 STRATEGY FOR CLASSROOM MONITORING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 2, page no.c442-c451, February-2025, Available :http://www.jetir.org/papers/JETIR2502253.pdf

"IMAGE INTERPRETATION ANALYSIS UTILIZING THE FLORENCE 2 STRATEGY FOR CLASSROOM MONITORING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 2, page no. ppc442-c451, February-2025, Available at : http://www.jetir.org/papers/JETIR2502253.pdf