Emotion Prediction Based on Real-Time Crowd Analysis Using Deep Network

Emotions are complex mental states that involve changes in neurophysiology, thoughts, feelings, and behavioral responses. In a crowd, emotions can become amplified and have a significant impact on the overall mood and behavior of the group. The emotions of individuals in a crowd can have a significant impact on the overall mood and behavior of the group. With the advancements in facial recognition technology, it is now possible to detect the emotions displayed on the faces of individuals in a crowd. This technology can be incredibly useful in a variety of ways, such as identifying the intent of a crowd, promoting offers, or identifying security threats. This paper discusses the deep learning approach for crowd emotion detection. A convolutional neural network (CNN) algorithm is trained on Facial Expression Recognition 2013 Dataset (FER-13) dataset. The input to the model is a live video feed featuring a crowd of people. The multiple faces in the video frames are processed by the CNN model. Further, the model detects the emotions in the faces. The performance of the model is promising in facial emotion recognition in crowded environments.