Towards a comprehensive 3D dynamic facial expression database

Abstract

Human faces play an important role in everyday life, including the expression of person identity, emotion and intentionality, along with a range of biological functions. The human face has also become the subject of considerable research effort, and there has been a shift towards understanding it using stimuli of increasingly more realistic formats. In the current work, we outline progress made in the production of a database of facial expressions in arguably the most realistic format, 3D dynamic. A suitable architecture for capturing such 3D dynamic image sequences is described and then used to record seven expressions (fear, disgust, anger, happiness, surprise, sadness and pain) by 10 actors at 3 levels of intensity (mild, normal and extreme). We also present details of a psychological experiment that was used to formally evaluate the accuracy of the expressions in a 2D dynamic format. The result is an initial, validated database for researchers and practitioners. The goal is to scale up the work with more actors and expression types.