How to plot a marker around eye region according to face landmarks of mediapipe Python

Question

The question is how to find the eye coordinate using the multipipe library and place a marker at the left,right, top, and bottom of each of the eyes using cv2 library. as shown in the image below.

One of alternate suggestion is given below. I save this as my and other future reference

This is the continuation from this OP

Image taken from this link

Answer 1

This can be achieve via mp.solutions.face_mesh.FaceMesh

First get the face bb

results = face_mesh.process(cv2.cvtColor(image_input , cv2.COLOR_BGR2RGB))

Then for each eye region of interest, get the pixel position using the _normalized_to_pixel_coordinates

eye_r = _normalized_to_pixel_coordinates()

The full code is as below

import cv2
import mediapipe as mp

from mediapipe.python.solutions.drawing_utils import _normalized_to_pixel_coordinates

dframe = cv2.imread("detect_face/person.png")

image_input = cv2.cvtColor(dframe, cv2.COLOR_BGR2RGB)

face_mesh = mp.solutions.face_mesh.FaceMesh(static_image_mode=True, max_num_faces=2,
                                         min_detection_confidence=0.5)
image_rows, image_cols, _ = dframe.shape
results = face_mesh.process(cv2.cvtColor(image_input , cv2.COLOR_BGR2RGB))

fl=results.multi_face_landmarks[0]


##

for txt,cor in zip(['L','R','T','B'],[263, 362,386,374]):
    eye_r = _normalized_to_pixel_coordinates(fl.landmark[cor].x,fl.landmark[cor].y,
                                             image_cols,image_rows)
    cv2.putText(image_input, txt, eye_r,cv2.FONT_HERSHEY_SIMPLEX, 0.3, (0, 0, 255), 2)
    
for txt,cor in zip(['l','r','t','b'],[133,33,159,145]):
    eye_r = _normalized_to_pixel_coordinates(fl.landmark[cor].x,fl.landmark[cor].y,
                                             image_cols,image_rows)
    cv2.putText(image_input, txt, eye_r,cv2.FONT_HERSHEY_SIMPLEX, 0.3, (0, 0, 255), 2)



cv2.imwrite('test.png', image_input)

Which output