FER2013

Facial Expression Recognition 2013 Dataset

ImagesUnknownIntroduced 2013-01-01

Fer2013 contains approximately 30,000 facial RGB images of different expressions with size restricted to 48×48, and the main labels of it can be divided into 7 types: 0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral. The Disgust expression has the minimal number of images – 600, while other labels have nearly 5,000 samples each.

Source: Eavesdrop the Composition Proportion of Training Labels in Federated Learning Image Source: https://medium.com/@birdortyedi_23820/deep-learning-lab-episode-3-fer2013-c38f2e052280

Benchmarks

3D/Accuracy 3D Face Modelling/Accuracy 3D Face Reconstruction/Accuracy Emotion Recognition/5-class test accuracy Face Reconstruction/Accuracy Facial Expression Recognition/Accuracy Facial Expression Recognition (FER)/Accuracy Facial Recognition and Modelling/Accuracy Image Clustering/Accuracy Image Compression/10%