Deep Convolutional Neural Network for Real-Time Facial Expression Detection

Facial Emotional Recognition is an interesting topic with a wide range of various applications such as image and video retrieval, automated tutoring systems, human-computer interaction, and driver warning systems. Facial expression is one of the nonverbal communication. With the help of analyzing human facial emotion, the inner feelings and real emotions of a person can be identified. Capturing the dynamics of facial expression progression in the video is an essential and challenging task for facial expression recognition (FER). The proposed system uses a new low-cost and multi-user framework based on big data analysis for patient feelings, where emotion is detected in terms of facial expression. A Faster region convolutional neural network (FRCNN) is applied to the whole facial observation to learn the global characteristics of six different expressions namely Happy, Sad, anger, surprise, and neutral. Finally, the Predicted emotions are shown as output.