Is 2D Unlabeled Data Adequate for Recognizing Facial Expressions?

Automatic facial expression recognition is one of the important challenges for computer vision and machine learning. Despite the fact that many successes have been achieved in recent years, several important but unresolved problems remain. This article describes a facial expression recognition system based on the random forest technique. Contrary to the many previous methods, the proposed system uses only simple landmark features, with the view of possible real-time implementation on low-cost portable devices. Both supervised and unsupervised variants of the method are presented. However, the authors' main objective is to provide some quantitative experimental evidence behind more fundamental questions in facial articulation analysis, namely, the relative significance of 3D information as opposed to 2D data only and the importance of labeled training data in supervised learning as opposed to unsupervised learning. The comprehensive experiments were performed using the BU-3DFE facial expression database. These experiments not only show the effectiveness of the described methods but also demonstrate that the common assumptions about facial expression recognition are debatable.