Knowledge Base

Subject Characteristics

This option is not available with Baby FaceReader.

To Access This Option

Click the Select window button in one of the visualization windows, select Face Analysis, and then Subject Characteristics.

Subject Characteristics

The Subject Characteristics table displays the following:

• Gender – A range is given with a certainty value. If the gender is entered manually in the Independent Variables, the value is fixed and the certainty is 100%.
• Age – A range is given with a certainty value. If the age is entered manually in the Independent Variables, the value is fixed and there is no certainty displayed in the table.
• Presence of glasses – A certainty value is given.

Note

The Subject Characteristics table also gives you an indication of the quality of the image. If the quality of your image is poor, the information will not be correct. For instance, if FaceReader reports that a female test person is male, then the modeling is not correct, most probably because the image is of poor quality or the lighting conditions are bad.

Valence And Arousal Line Chart

To Access This Option

Click the Select window button in one of the visualization windows, and select Face Analysis and then Valence and Arousal Line Chart.

Valence

Valence indicates whether the facial expressions display a positive or negative emotion.

See the figure below for an example. When you play back the video, a hairline shows the time in the video.

How Valence Is Calculated

The valence indicates whether the emotional status of the subject is positive or negative. 'Happy' is the only positive emotion, 'Sad', 'Angry', 'Scared' and 'Disgusted' are considered to be negative emotions. 'Surprised' can be either positive or negative and is, therefore, not included in the calculation of valence. Contempt is also not included in the calculation of Valence.

Valence is calculated as the intensity of 'Happy' minus the intensity of the negative emotion with the highest intensity.

If you have Baby FaceReader, Valence is based on Action Units.

Example

Consider the following expression intensities:

• Happy – 0.8
• Sad – 0.1
• Angry – 0.0
• Scared – 0.05
• Disgusted – 0.05

In this case Valence is 0.8 - 0.1 = 0.7.

Arousal

Arousal indicates whether the test participant's face is active (+1) or not active (0). Arousal is based on the activation of 20 Action Units (AUs) of the Facial Action Coding System (FACS).

See the figure above for an example. When you play back the video, a hairline shows the time in the video.

How Arousal Is Calculated

1. The activation values (AV) of 20 AUs are taken as input. These are AU 1, 2, 4, 5, 6, 7, 9, 10, 12, 14, 15, 17, 18, 20, 23, 24, 25, 26, 27, and the inverse of 43. The value of AU43 (eyes closed) is inverted because it indicates low arousal instead of high arousal like the other AUs.
2. The arousal is calculated by taking the mean of the three highest values.

Note

• Contempt is not included in the calculation of Arousal.

Source: FaceReader 10 Reference Manual (Help), Noldus Information Technology