Emotion Recognition Model Based on Visual Cues and Explainable AI Using Facial Expression Video

Emotion recognition is vital for improving human-computer interaction by enabling systems to interpret and respond to human emotions. This project presents a real-time emotion recognition framework integrating TensorFlow-based Convolutional Neural Networks (CNNs) for emotion classification and YOLOv10 for accurate face detection. The model leverages Explainable AI (XAI) techniques, such as Grad-CAM, to ensure transparency by visualizing critical facial features that influence predictions. Built on the FER2013 dataset, the framework demonstrates a robust combination of accuracy and interpretability, effectively handling diverse facial expressions in dynamic environments. The system excels in applications like mental health monitoring, adaptive user interfaces, and customer engagement platforms. While challenges remain in refining the classification of subtle emotions, the integration of advanced detection and interpretability methods establishes a solid foundation for the development of emotion-aware technologies, emphasizing both reliability and user trust.