Figure 7
From: Impact of Affective Multimedia Content on the Electroencephalogram and Facial Expressions
Illustrating the working of our algorithm through (A) a sample image frame, (B) extracted face region and locating facial landmarks, and (C) 30 distance/area features computed based on the facial landmarks. To account for different face sizes and distance from the camera, all features were re-scaled based on face width (W) and face height (H). A sample image was used to generate this figure in order to respect the privacy of the users who participated in the study.
