This project aims to classify the emotion on a person's face into one of seven categories, using deep convolutional neural networks. This algorithm is based on the research paper from emotion-recognition-neural-networks.
-
This code has been tested on Ubuntu 16.04 LTS and is most likely compatible on all platforms.
-
Dependencies: Python 3.5+, OpenCV 3.0, TFlearn.
-
Clone the repository and download the trained model files from here, extract it and copy the files into the current working directory.
-
To run the program to detect emotions only in one face, type
python em_model.py singleface. -
To run the program to detect emotions on all faces close to camera, type
python em_model.py multiface.
-
First, we use haar cascade to detect faces in each frame of the webcam feed.
-
The region of image containing the face is resized to 48x48 and is passed as input to the ConvNet.
-
The network outputs a list of softmax scores for the seven classes.
-
The emotion with maximum score is displayed.
