Table 2.
Percentage of frames correctly identified by classifier: Azure (Azure Cognitive Services), AWS (Amazon Web Services), SH (Sighthound), and Google (Google Cloud Vision). These results only include frames in which there was a face, and the two manual raters agreed on the class. Google Vision API does not support the neutral label.
| Classifier | Frame type | ||
|
|
Emotive (n=1209), n (%) | Neutral (n=1393), n (%) | All (n=2602), n (%) |
| Azure | 798 (66.00) | 744 (53.40) | 1542 (59.26) |
| AWSa | 829 (68.56) | 679 (48.74) | 1508 (57.95) |
| 785 (64.92) | N/Ab | N/A | |
| Sighthound | 664 (54.92) | 902 (64.75) | 1566 (60.18) |
aAWS: Amazon AWS Rekognition.
bN/A: not applicable.