Prioritizing the health and well-being of students is crucial in today's educational settings in order to promote both individual development and cooperative team dynamics. Taking into account the significant influence that emotional states have on academic performance, this study highlights the necessity of a proactive strategy to monitor and improve students' emotional well-being in the classroom. In the last few decades, machine learning-based automatic facial expression analysis has become a vibrant and fascinating area of study. This study presents the Real-Time Student Emotion Detection System (RtSED), a revolutionary solution that uses cutting-edge machine learning techniques to track and recognize student emotions in real-time autonomously. Teachers can evaluate students' emotional states instantly with the use of the RtSED system, which is a useful tool. The system's incorporation of machine learning algorithms enables it to precisely identify a range of emotions, giving teachers vital information about their pupils' wellbeing. Furthermore, the recognized emotions are conveyed to the corresponding students via customized messages, empowering them to acquire consciousness and make knowledgeable choices regarding their emotional conditions.