The data consists of 48x48 pixel grayscale images of faces. The network classifies each face based on the emotion shown in the facial expression into one of seven categories (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral). Uses OpenCV to automatically detect faces in images and draw bounding boxes around them. The trained model is directly served to a web interface and performs real-time facial expression recognition on video and image data.
The data can be found here