Performance Analysis of Face and Emotion Recognition Systems in Video Conference Based on Web Application

This research tackles the difficulty of evaluating emotions in online education, where restricted interaction impedes comprehension. Our proposal is a web application constructed on the Google Cloud Platform, Vercel, Next.js, and FastAPI, which employs a Convolutional Neural Networks (CNNs) model for real-time emotion recognition during online courses. By capturing conference video and analyzing participant faces in screenshots, the application presents emotions on a user-friendly dashboard. Although the front-end performance shows potential, back-end optimization is necessary. This application possesses the potential to improve emotion assessment and ultimately enhance online learning results.