Table 1.
Descriptive statistics for facial expressions.
| Males | Females | |||||||
|---|---|---|---|---|---|---|---|---|
| Mean | SD | Min | Max | Mean | SD | Min | Max | |
| Anger | 0.00 | 0.01 | 0.00 | 0.35 | 0.00 | 0.00 | 0.00 | 0.03 |
| Contempt | 0.01 | 0.03 | 0.00 | 0.45 | 0.00 | 0.02 | 0.00 | 0.25 |
| Disgust | 0.00 | 0.01 | 0.00 | 0.10 | 0.00 | 0.01 | 0.00 | 0.09 |
| Fear | 0.00 | 0.00 | 0.00 | 0.02 | 0.00 | 0.00 | 0.00 | 0.01 |
| Happiness | 0.79 | 0.32 | 0.00 | 1.00 | 0.92 | 0.19 | 0.00 | 1.00 |
| Neutral | 0.19 | 0.30 | 0.00 | 1.00 | 0.08 | 0.18 | 0.00 | 1.00 |
| Sadness | 0.00 | 0.02 | 0.00 | 0.35 | 0.00 | 0.01 | 0.00 | 0.25 |
| Surprise | 0.00 | 0.00 | 0.00 | 0.06 | 0.00 | 0.00 | 0.00 | 0.01 |
The scores are based on the training samples since this is the largest sample and represents what the model has “learned.” Each face is identified as representing a given expression to a given degree. Thus, a given face could be scored as primarily similar to happiness (0.65), but also similar to a neutral expression (0.35).