I'm trying to extract the mean colour of few point of the face using the media pipe library. The below code is to print the needed points on the face. But not sure on how to add each of these points and get the mean RGB value of the points

import cv2
import mediapipe as mp
from mediapipe.python.solutions import face_mesh
import numpy as np

#init main point array
color_array = []

#to access facemesh lib from mediapipe to identify facial landmarks
mpFaceMesh = mp.solutions.face_mesh
face_mesh = mpFaceMesh.FaceMesh()

#getting image
image = cv2.imread("E:\BeautBeta\IP_application/test2.jpg") #test: cannot add with multiple faces
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) 
height, width, _ = image.shape

#process image
result = face_mesh.process(rgb_image)
for facialLandmarks in result.multi_face_landmarks:
    
#specific landmarks are detected through the mediapipe library are considered here because not all landmarks are valid
    
landmarks_array = [3, 6, 8, 9, 32, 36, 69, 67, 109, 108, 101, 116, 117, 135, 16, 148, 151, 172, 169, 171, 152, 165, 170, 175, 199, 194, 192, 187, 200, 211, 204, 202, 207, 206, 210, 216, 228, 229, 266, 262, 277, 275, 273, 280, 281, 297, 299, 298, 330, 323, 343, 338, 337, 333, 343, 349, 348, 347, 350, 371, 357, 351, 396, 377, 391, 393, 423, 411, 420, 419, 421, 418, 422, 424, 429, 437, 425, 426, 432, 427, 436, 434, 430, 431, 428, 449, 448, 450, 451, 452]
    for i in landmarks_array:
        pt =facialLandmarks.landmark[i]
        x = int(pt.x * width)
        y = int(pt.y * height)
        ptcor = (x,y)
        cv2.circle(image, (x,y), 3, (255,255,255), -1)
        color_array.append(ptcor)

mean_cor = np.mean(color_array, axis=0)
print(mean_cor)        
cv2.imshow("Image", image)
cv2.waitKey(0)

CodePudding user response：

In your code ptcor = (x,y) are coordinates.

May be you want ptcor = rgb_image[y][x] that is the rgb color of those coordinates