Benchmarking commercial emotion detection systems using realistic distortions of facial image datasets

• Published in: The Visual computer Vol. 37; no. 6; pp. 1447 - 1466
• Main Authors: Yang, Kangning, Wang, Chaofan, Sarsenbayeva, Zhanna, Tag, Benjamin, Dingler, Tilman, Wadley, Greg, Goncalves, Jorge
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2021; Springer Nature B.V
• Subjects: Affect (Psychology); Algorithms; Artificial Intelligence; Cameras; Cloud computing; Communication; Computer Graphics; Computer Science; Emotion recognition; Emotions; Image classification; Image manipulation; Image Processing and Computer Vision; Image resolution; Machine learning; Original Article; Performance evaluation; Physiology; Researchers; Smartphones; Software; Affective computing; Validation analysis; Non-ideal conditions; Commercial emotion recognition systems; Facial emotion recognition

Currently, there are several widely used commercial cloud-based services that attempt to recognize an individual’s emotions based on their facial expressions. Most research into facial emotion recognition has used high-resolution, front-oriented, full-face images. However, when images are collected...