Note: This is a messy repository, you should find your way through what is present here (unfortunately).
- Alex Young
- Andreas Eliasson
- Ara Hayrabedian
- Lukas Weiss
- Utku Ozbulak
The data consists of 48x48 pixel grayscale images of faces. The faces have been automatically registered so that the face is more or less centered and occupies about the same amount of space in each image. The task is to categorize each face based on the emotion shown in the facial expression in to one of seven categories (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral).
The training set consists of 28,709 examples. The first test set consists of 3,589 examples. The final test set consists of another 3,589 examples.
This dataset was prepared by Pierre-Luc Carrier and Aaron Courville, as part of an ongoing research project in the past.
Past Kaggle competition for this partical challenge: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge
Angry
Disgust
Fear
Happy
Sad
Surprise
Neutral
~50% Accuracy on detected faces with SVMs
SVM Optimisation:
~49% Accuracy on detected faces with neural nets
~28% Accuracy on detected faces with SVMs
~51% Accuracy on all data (7 classes)
CNN Model Breakdowns:
~49% Accuracy with bagged model
Supposed to be: Surpsised Found: 93% Neutral - 3% Sad
Supposed to be: Angry Found: 43% Sad - 21% Angry
Supposed to be: Happy Found: 86% Happy - 11% Neutral
Supposed to be: Neutral Found: 83% Neutral - 7% Angry
Supposed to be: Sad Found: 33% Sad - 25% Fear
Supposed to be: Fear Found: 94% Neutral - 4% Fear