principle

face_recognition It is the simplest face recognition database , The accuracy of the model is 99.38%
The code only needs three lines ：

import face_recognition
image = face_recognition.load_image_file("your_file.jpg")
face_locations = face_recognition.face_locations(image)

One 、 Results the preview

face_locations Return the coordinate positions of all faces in the picture , coordination cv2 The library draws all the coordinates on the picture .

Two 、 Implementation process

import face_recognition
import cv2
​
# Loading pictures 
image = face_recognition.load_image_file("1.jpg")
# Recognize the position of all faces in the picture 
face_locations = face_recognition.face_locations(image)
​
img = cv2.imread("1.jpg", cv2.IMREAD_COLOR)
​
for i in face_locations:
    #face_locations  Return parameter position description  (top, right, bottom, left)
    top = i[0]
    right = i[1]
    bottom = i[2]
    left = i[3]
​
    # param 1: picture 
    # param 2: Top left coordinates 
    # param 3: Lower right coordinates 
    # param  Box color 
    #  Box size 
    cv2.rectangle(img, (left, top), (right, bottom), (255, 255, 255), 2)
    #  display picture 
    cv2.imshow("1.jpg", img)
    #  Save as new file 
    cv2.imwrite("new.jpg", img)
​
cv2.waitKey(0)
cv2.destroyAllWindows()