OpenCV 4 with Python Blueprints - Second Edition

Transforming the face

Transforming the face is a standard process that can be achieved by warping the image using cv2.warpAffine (recall Chapter 3, Finding Objects via Feature Matching and Perspective Transforms). We will follow the next steps to achieve this transformation:

1. First, we calculate the angle (in degrees) between the line that connects the two eyes and a horizontal line, as follows:

        eye_angle_deg = 180 / np.pi * np.arctan2(right_eye[1]                                                  - left_eye[1],                                                 right_eye[0]                                                  - left_eye[0])

2. Then, we derive a scaling factor that will scale the distance between the two eyes to be exactly 50% of the image width, like this:

        eye_dist = np.linalg.norm(left_eye - right_eye)        eye_size_scale = (1.0 - desired_eye_x * 2) *  desired_img_width / ...