Ask Your Question

Revision history [back]

As stated by yourself, the coordinates of the bounding box of any returned face/eye detection is of the form x_upper_left_corner y_upper_left_corner width height keeping in mind that the origin of OpenCV is at the upper left image corner.

You can easily use these parameters to apply some normalization of faces, as discussed in OpenCV 3 Blueprints, chapter 6, and as seen in the code for that chapter, right here.