I am developing a model for feature counting on a person's face that consumes three photos (one face forward and two profile pictures). My model can already detect features, but it counts some features twice.
Consider the image below. There are only four labels (1, 2, 3, 4 and 5). Model detects four labels (1, 2, 3, 4) on the profile photo and four labels on the face forward photo (1, 2, 3, 5).
Labels (1, 2, 3) are counted twice. A straightforward approach would be to segment hundreds of faces into "face forward region" and "profile region". This is tedious and accurate labeling is hard. Is there a better way to segment the face in regions or to detect duplication of the detected features?