Going deeper in hidden sadness recognition using spontaneous micro expressions database

Abstract

Recognition of facial micro-expressions (MEs), which indicates conscious or unconscious suppressing of true emotions, is still a challenging task in the affective computing and computer vision. There are two main reasons for that: First, the lack of spontaneous MEs databases, preferably focused on one emotion. So far, posed facial MEs databases were developed, and in the most cases, machines were trained on this posed MEs, which are stronger and more visible than spontaneous ones. Second, in order to achieve high recognition rate, deep learning structures are required that can achieve the best performance with very large number of data. To address these challenges, we make the following contributions: (i) extension of our MEs spontaneous database by adding new subjects; (ii) We analysed spontaneous MEs in long videos only for hidden sadness; (iii) We presented deeper analysis for automatic hidden sadness detection algorithm with deep learning architecture and compared results with standard machine learning techniques for hidden sadness detection. It is shown that with our method 99.08% recognition performance has been achieved observing only the eye region of the face.