Using Hankel Matrices for Dynamics-based Facial Emotion Recognition and Pain Detection
This work addresses the problem of improving facial emotion and pain detection for applications in healthcare or human-computer interaction, but it is incremental as it builds on existing classification frameworks.
The paper tackled modeling temporal dynamics in facial expression sequences by representing them as outputs of a Linear Time Invariant system using Hankel matrices, achieving competitive performance in emotion recognition and pain detection on public benchmarks.
This paper proposes a new approach to model the temporal dynamics of a sequence of facial expressions. To this purpose, a sequence of Face Image Descriptors (FID) is regarded as the output of a Linear Time Invariant (LTI) system. The temporal dynamics of such sequence of descriptors are represented by means of a Hankel matrix. The paper presents different strategies to compute dynamics-based representation of a sequence of FID, and reports classification accuracy values of the proposed representations within different standard classification frameworks. The representations have been validated in two very challenging application domains: emotion recognition and pain detection. Experiments on two publicly available benchmarks and comparison with state-of-the-art approaches demonstrate that the dynamics-based FID representation attains competitive performance when off-the-shelf classification tools are adopted.