Automatic recognition system of emotions expressed through the face using machine learning: Application to police interrogation simulation

During our work, we developed Automatic recognition system of emotions expressed through the face. This system will be adapted to judicial police interrogation or interviews simulation. This system is based on a functional division: detection and follow-up the face, acquisition of facial expressions starting from video images sequences, and finally, characteristics extraction and emotions expressed recognition. The deep convolution network model is formed primarily on FER2013. It is used to train and validate the model. We use OpenCV library and its implementation of the Viola and Jones algorithm for face detection.