Dynamic facial landmarking selection for emotion recognition using Gaussian processes

Facial features are the basis for the emotion recognition process and are widely used in affective computing systems. This emotional process is produced by a dynamic change in the physiological signals and the visual answers related to the facial expressions. An important factor in this process, relies on the shape information of a facial expression, represented as dynamically changing facial landmarks. In this paper we present a framework for dynamic facial landmarking selection based on facial expression analysis using Gaussian Processes. We perform facial features tracking, based on Active Appearance Models for facial landmarking detection, and then use Gaussian process ranking over the dynamic emotional sequences with the aim to establish which landmarks are more relevant for emotional multivariate time-series recognition. The experimental results show that Gaussian Processes can effectively fit to an emotional time-series and the ranking process with log-likelihoods finds the best landmarks (mouth and eyebrows regions) that represent a given facial expression sequence. Finally, we use the best ranked landmarks in emotion recognition tasks obtaining accurate performances for acted and spontaneous scenarios of emotional datasets.