AUTHOR=Küntzler Theresa , Höfling T. Tim A. , Alpers Georg W. TITLE=Automatic Facial Expression Recognition in Standardized and Non-standardized Emotional Expressions JOURNAL=Frontiers in Psychology VOLUME=Volume 12 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2021.627561 DOI=10.3389/fpsyg.2021.627561 ISSN=1664-1078 ABSTRACT=Emotional facial expressions can inform researchers about an individual's emotional state. Recent technological advances open new avenues to automatic Facial Expression Recognition (FER). Based on machine learning, such technology can tremendously increase the amount of processed data. This technology is now easily accessible and has been validated for standardized prototypical facial expressions. However, applicability for more naturalistic facial expressions still remains uncertain. Hence, we tested and compared performance of three different FER systems (Azure Face API, Microsoft; Face++, Megvii Technology; FaceReader, Noldus Information Technology) with human emotion recognition A) for standardized acted facial expressions (from prototypical inventories) and B) for non-standardized acted facial expressions (extracted from emotional movie scenes). For the standardized images, all three systems classify basic emotions accurately (FaceReader is most accurate) and they are mostly on par with human raters. For the non-standardized stimuli, performance drops remarkably for all three systems, but Azure still performs similar to humans. In addition, all systems and humans alike tend to classify some of the non-standardized emotional facial expressions as neutral. In sum, emotion recognition by automated facial expression recognition can be an attractive alternative for human emotion recognition for standardized and non-standardized emotional facial expressions. However, we also found limitations in accuracy for specific facial expressions; clearly there is need for thorough empirical evaluation to guide future developments in computer vision.