Facial expression recognition is a crucial component for improving human-AI interaction and represents a core problem in computer vision, with applications in areas such as image captioning and behavioral analysis. The goal of this project is to develop a model which is capable of detecting faces and classifying emotional expressions accurately, particularly in group image settings. To achieve this, the project employs two complementary deep learning approaches: a fine-tuned YOLO model for a single step face and emotion detection, and a two-stage framework that integrates an automatic face detector with a fine-tuned emotion classifier for refined prediction.