Unbiased Mimic Activity Evaluation: F2F Emotion Studio Software

Abstract

We developed a research software which allows users to accurately detect FACS AUs and basic emotion expressions. This software was developed as a comprehensive FACS based measurement tool. Due to their inherent limitations we don't use any kind of neural network facial expression classification. We created five author's computer vision procedures and a set of logical rules to detect 18 AUs and seven basic emotion expressions. The software could evaluate both macro- and microexpressions. As evaluation results we provided three examples of analyzing data taken from the SAMM and CASME II databases using F2F Emotion Studio software.