Real time Face Detection Blog

cnn-realtime.py

# import required packages
import dlib
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 = 'video/face-demographics-walking.mp4'
video_stream = cv2.VideoCapture(video_file_path)

# initialize dlib's face detectors
# CNN face detector with mmod_human_face_detector.dat weights
weights = 'models/mmod_human_face_detector.dat'
cnn_face_detector = dlib.cnn_face_detection_model_v1(weights)

# 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 cnn_face_detector
  # First argument is the image array
  # The 1 in the second argument indicates that we should upsample the image
  # 1 time. This will make everything bigger and allow us to detect more smaller faces from the image.
  all_face_locations = cnn_face_detector(scaled_frame, 1)

  for index,face_location in enumerate(all_face_locations):
    
    # split the tuple 
    # scale up the coordinates by 2 times
    top_pos = face_location.rect.top() * 2
    right_pos = face_location.rect.right() * 2
    bottom_pos = face_location.rect.bottom() * 2
    left_pos = face_location.rect.left() * 2

    # 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("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()

detect-faces-from-video-frames.py

# 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 hog_face_detector
  # First argument is the image array
  # The 1 in the second argument indicates that we should upsample the image
  # 1 time. This will make everything bigger and allow us to detect more smaller faces from the image.
  all_face_locations = hog_face_detector(scaled_frame, 1)

  for index,face_location in enumerate(all_face_locations):
    
    # split the tuple 
    # scale up the coordinates by 2 times
    top_pos = face_location.top() * 2
    right_pos = face_location.right() * 2
    bottom_pos = face_location.bottom() * 2
    left_pos = face_location.left() * 2

    # 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("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()

dir-tree.md

•
├── video
│   └── face-demographics-walking.mp4
├── models
│   └── mmod_human_face_detector.dat
├── cnn-realtime-face-detection.py
├── hog-realtime-face-detection.py
└── face-recognition-realtime-face-detection.py

hog-realtime.py

# import required packages
import dlib
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 = 'video/face-demographics-walking.mp4'
video_stream = cv2.VideoCapture(video_file_path)

# initialize HOG face detection model
hog_face_detector = dlib.get_frontal_face_detector()

# 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 hog_face_detector
  # First argument is the image array
  # The 1 in the second argument indicates that we should upsample the image
  # 1 time. This will make everything bigger and allow us to detect more smaller faces from the image.
  all_face_locations = hog_face_detector(scaled_frame, 1)

  for index,face_location in enumerate(all_face_locations):
    
    # split the tuple 
    # scale up the coordinates by 2 times
    top_pos = face_location.top() * 2
    right_pos = face_location.right() * 2
    bottom_pos = face_location.bottom() * 2
    left_pos = face_location.left() * 2

    # 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("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()

import-libraries.py

# import required packages
import dlib
import cv2

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

initialize-video-stream.py

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

# initialize HOG face detection model
hog_face_detector = dlib.get_frontal_face_detector()

realtime-face-detection.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 = 'video/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

    # 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("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()