This model can detect 7 different emotions (happy, sad, angry, surprise, fear, disgust and neutral) of human face in Realtime cam or Image or Video.The model is built using deep convolutional network and trained on the FER-2013 dataset which was published on International Conference on Machine Learning (ICML).
- on train set: 94.96%
- on test set: 66.6%
click here to show dependencies
- This dataset consists of 35887 grayscale, 48x48 sized face images with seven emotions - angry, disgust, fear, happy, neutral, sad and surprise.
- download the fer2013 dataset from here
Licensed under MIT Licencse
"Convolutional Neural Networks for Facial Expression Recognition" Convolutional Neural Networks for Facial Expression Recognition Shima Alizadeh, Azar Fazel