Face Blurring Blog

blur-face-from-image.py

# load the image to be detected
image = cv2.imread('test/family.jpg')

# find all face locations using face_locations() function
# model can be "cnn" or "hog"
# number_of_times_to_upsample = 1 higher and detect more smaller faces from the image
all_face_locations = face_recognition.face_locations(image, model="hog")

#printing the number of faces in the array
print("There are {} face(s) in this image".format(len(all_face_locations)))

# create copy of original image
bbox_image = image.copy()

# loop over each face detected in the image
# draw box over the image
for face_location in all_face_locations:
  
  top_pos, right_pos, bottom_pos, left_pos = face_location
  
  #---------------------------------------------------------------------------
  # Face Blurring
  #---------------------------------------------------------------------------

  # Slice frame image array by positions face_locations
  face_image = bbox_image[top_pos:bottom_pos, left_pos:right_pos]

  # Blur the current face image
  face_image = cv2.GaussianBlur(face_image, (99,99), 30)

  # Put the blurred face region back into the frame image
  bbox_image[top_pos:bottom_pos, left_pos:right_pos] = face_image

  #---------------------------------------------------------------------------

  # draw bbox around face
  bbox_image = cv2.rectangle(bbox_image, (left_pos,top_pos), (right_pos,bottom_pos), (0,0,255), 2)

# show image
cv2.imshow("Blurred Faces",bbox_image)

# only for google colab 
# cv2_imshow(bbox_image)

dir-tree.md

•
├── test
│   ├── family.jpg
│   └── face-demographics-walking.mp4
├── face-blurring-on-image.py
└── realtime-face-blurring.py

import-libraries.py

# import required packages
import face_recognition
import cv2

# only for google colab
# from google.colab.patches import cv2_imshow

realtime-face-blurring.py

# import required packages
import face_recognition
import cv2

# only for google colab
# from google.colab.patches import cv2_imshow

# for using your inbuilt webcam
# Get the webcam #0 ( the default one, 1, 2 and so on)
# video_stream = cv2.VideoCapture(0)

# for using video file
video_file_path = 'test/face-demographics-walking.mp4'
video_stream = cv2.VideoCapture(video_file_path)

# initialize the number of frame needed to be skipped
skip = 0

while True:

  #Read the frame
  for i in range(skip):
      video_stream.grab()

  # get current frame
  stat, frame = video_stream.read()

  # check that frame is left to read
  if stat == False:
    print('Video has ended')
    break  

  # reduce size of image to 50%
  scaled_frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5)

  # find all face locations using face_locations() function
  # model can be "cnn" or "hog"
  # number_of_times_to_upsample = 1 higher and detect more faces

  all_face_locations = face_recognition.face_locations(scaled_frame, model="cnn")

  for index,face_location in enumerate(all_face_locations):

    # split the tuple 
    top_pos, right_pos, bottom_pos, left_pos = face_location

    # scale up the coordinates by 2 times
    top_pos = top_pos * 2
    right_pos = right_pos * 2
    bottom_pos = bottom_pos * 2
    left_pos = left_pos * 2

    #---------------------------------------------------------------------------
    # Face Blurring
    #---------------------------------------------------------------------------

    # Slice frame image array by positions face_locations
    face_image = frame[top_pos:bottom_pos, left_pos:right_pos]

    # Blur the current face image
    face_image = cv2.GaussianBlur(face_image, (99,99), 30)

    # Put the blurred face region back into the frame image
    frame[top_pos:bottom_pos, left_pos:right_pos] = face_image

    #---------------------------------------------------------------------------

    # draw rectangle around each face
    frame = cv2.rectangle(frame, (left_pos,top_pos), (right_pos,bottom_pos), (0,0,255), 2)

  # display frame
  cv2.imshow("Blurred Face Video",frame)

  # for only google colab
  # cv2_imshow(frame)
  
  # Press 'q' on the keyboard to break the while loop
  if cv2.waitKey(1) & 0xFF == ord('q'):
    break

# Release the video stream resource
video_stream.release()
cv2.destroyAllWindows()