Deep Pain: Exploiting Long Short-Term Memory Networks for Facial Expression Classification

Pain is an unpleasant feeling that has been shown to be an important factor for the recovery of patients. Since this is costly in human resources and difficult to do objectively, there is the need for automatic systems to measure it. In this paper, con- trary to current state-of-the-art techniques in pain assessment, which are based on facial features only, we suggest that the performance can be enhanced by feeding the raw frames to deep learning models, outperforming the latest state-of-the-art results while also directly facing the problem of imbalanced data. As a baseline, our approach first uses convolutional neural networks (CNN) to learned facial features from VGG Faces, which are then linked to a Long Short-Term Memory (LSTM) to exploit the temporal relation between video frames. We further compare the performances of using the so popular schema based on the canonically normalized appearance versus taking into account the whole image: As a result, we outperform current state- of-the-art AUC performance in the UNBC-McMaster Shoulder Pain Expression Archive Database. In addition, to evaluate the generalization properties of our proposed methodology on facial motion recognition, we also report competitive results in the Cohn Kanade+ facial expression database.