How to do it...

1. Import the necessary packages:

import cv2 
import numpy as np 

2. Load the face cascade file:

frontalface_cascade= cv2.CascadeClassifier('haarcascade_frontalface_alt.xml') 

3. Check whether the face cascade file has been loaded:

if frontalface_cascade.empty(): 
  raiseIOError('Unable to load the face cascade classifier xml file') 

4. Initialize the video capture object:

capture = cv2.VideoCapture(0) 

5. Define the scaling factor:

scale_factor = 0.5 

6. Perform the operation until the Esc key is pressed:

# Loop until you hit the Esc key 
while True: 

7. Capture the current frame and resize it:

  ret, frame = capture.read() 
  frame = cv2.resize(frame, None, fx=scale_factor, fy=scale_factor,  
            interpolation=cv2.INTER_AREA) 

8. Convert the image frame into grayscale:

  gray_image = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) 

9. Run the face detector on the grayscale image:

  face_rectangle = frontalface_cascade.detectMultiScale(gray_image, 1.3, 5)

10. Draw the rectangles box:

  for (x,y,w,h) in face_rectangle: 
    cv2.rectangle(frame, (x,y), (x+w,y+h), (0,255,0), 3) 

11. Display the output image:

    cv2.imshow('Face Detector', frame) 

12. Check whether the Esc key has been pressed for operation termination:

  a = cv2.waitKey(1) 
  if a == 10: 
    break 

13. Stop the video capturing and terminate the operation:

capture.release() 
cv2.destroyAllWindows() 

The result obtained in the human face detection system is shown here: