Abstract
The main goal of this paper is to perform an extensive analysis of the accuracy of six selected cloud-based facial emotion recognition services on three facial images datasets. The evaluation was performed on more than 33 000 images depicting eight different emotions. Results show that emotion recognition services show a varying level of accuracy over different types of datasets, having a lower accuracy for images of lower quality, but performing considerably better for images taken in ideal conditions. Based on these results we believe that cloud-based facial emotional recognition services do not have the expected accuracy for some use cases and therefore must be selected with care when developing a system that relies on emotion-based interactions.
Keywords
Cite this article
@article{cai-5545,
author = {Ján Magyar and Peter Sinčák and Ivan Čík and Andrinandrasana David Rasamoelina and Cindy L. Bethel and Filippo Cavallo and Ammar Hawbani},
title = {Experimental Evaluation of Cloud-Based Facial Emotion Recognition Services},
journal = {Computing and Informatics},
volume = {40},
number = {6},
pages = {1295--1321},
year = {2021},
issn = {1335-9150},
doi = {10.31577/cai_2021_6_1295}
}
TY - JOUR AU - Ján Magyar AU - Peter Sinčák AU - Ivan Čík AU - Andrinandrasana David Rasamoelina AU - Cindy L. Bethel AU - Filippo Cavallo AU - Ammar Hawbani TI - Experimental Evaluation of Cloud-Based Facial Emotion Recognition Services JO - Computing and Informatics VL - 40 IS - 6 SP - 1295 EP - 1321 PY - 2021 SN - 1335-9150 DO - 10.31577/cai_2021_6_1295 UR - https://doi.org/10.31577/cai_2021_6_1295 KW - Affective computing KW - cloud computing KW - facial emotion recognition KW - Software as a Service ER -
Magyar, J., Sinčák, P., Čík, I., Rasamoelina, A. D., Bethel, C. L., Cavallo, F., & Hawbani, A. (2021). Experimental Evaluation of Cloud-Based Facial Emotion Recognition Services. Computing and Informatics, 40(6), 1295–1321. https://doi.org/10.31577/cai_2021_6_1295