The FER2013 dataset is a set of over 28,000 labelled images used for training programs. This dataset is used in computer vision to develop AI that is able to recognize emotions through machine learning. It contains images that can be categorized into an index with 7 emotions where each emotion has its own pixel range:
0 = Angry
1 = Disgust
2 = Fear
3 = Happy
4 = Sad
5 = Surprise
6 = Neutral