FaceClassifier is an openFrameworks application, part of the ml4a-ofx collection, which rapidly lets you train a classifier to recognize facial expressions.
FaceClassifier is based on ofxFaceTracker2 and ofxGrt. It has been used by Andreas Refsgaard as part of integrating machine learning into the Eye Conductor project.
By default the app outputs OSC to localhost, port 8000, adress “/classification”. This can be changed in ofApp.h.
As an alternative to using the GUI you can use the following key inputs:
- 1-9: set the class label
- s: save model
- l: load model
- t: train classifier
- c: clear examples
- r: toggle recording
- p: pause prediction
To record training examples for class 1 make a distinct facial expression and click [record].
Set the Class Label slider to 2 and click [record] to record examples of a different facial expression.
Repeat this for class 3 or however many distinct expressions you want to classify. Remember to change the classes by pressing the numeric keys accordingly.
Click [train] to train the model.
Make facial expressions and see what class the model predicts.
The video below takes you through the steps of the training process.