Affiliation:
1. Ford Motor Company, Dearborn, MI, USA
Abstract
The work presented herein quantifies the limitations of the technology provided by two prominent suppliers in Emotion AI. Each Software Development Kit (SDK) performance was measured for accuracy using image and video databases. The results indicate that while the SDKs show high accuracy in detecting positive emotions (e.g., Happy), the performance suffered for negative emotions (e.g., Angry) due to missed and false detections. The results were worse for structured video datasets and degraded further when subjects were in naturalistic settings. Although Emotion AI have improved greatly in recent years, the current versions are not reliable enough for automotive applications. The paper provides perspectives on the reasons for subpar performance and guidance for improvement for future emotion estimation software.
Subject
General Medicine,General Chemistry
Reference12 articles.
1. Banerjee S., Brogan J., Krizaj J., Bharati A., Richard Webster B., Struc V., Flynn P., Scheirer W. (2018, March 27). To Frontalize or Not To Frontalize: Do We Really Need Elaborate Pre-processing To Improve Face Recognition? ArXiv.org. https://doi.org/10.48550/arXiv.1610.04823
2. “Eye can’t see the difference”: Facial Expressions of Pain, Pleasure, and Fear Are Consistently Rated Due to Chance
3. Crawford K. (2021, April 28). Artificial Intelligence Is Misreading Human Emotion. The Atlantic. https://www.theatlantic.com/technology/archive/2021/04/artificial-intelligence-misreading-human-emotion/618696/
4. Facial Action Coding System
5. Why faces don’t always tell the truth about feelings