Automatic stress analysis from facial videos based on deep facial action units recognition

Stress conditions are manifested in different human body's physiological processes and the human face. Facial expressions are modelled consistently through the Facial Action Coding System (FACS) using the facial Action Units (AU) parameters. This paper focuses on the automated recognition and analysis of AUs in videos as quantitative indices to discriminate between neutral and stress states. A novel deep learning pipeline for automatic recognition of facial action units is proposed, relying on two publicly available annotated facial datasets for training, the UNBC and the BOSPHORUS datasets. Two types of descriptive facial features are extracted from the input images, geometric features (non-rigid 3D facial deformations due to facial expressions) and appearance features (deep facial appearance features). The extracted facial features are then fed to deep fully connected layers that regress AU intensities and robustly perform AU classification. The proposed algorithm is applied to the SRD'15 stress dataset, which contains neutral and stress states related to four types of stressors. We present thorough experimental results and comparisons, which indicate that the proposed methodology yields particularly promising performance in terms of both AU detection and stress recognition accuracy. Furthermore, the AUs relevant to stress were experimentally identified, providing evidence that their intensity is significantly increased during stress, which leads to a more expressive human face as compared to neutral states.