├── README.md
├── cv_close_eye_detect.py
├── haarcascade_eye_tree_eyeglasses.xml
└── haarcascade_frontalface_alt.xml


/README.md:
--------------------------------------------------------------------------------
1 | # Closed-Eye-Detection-with-opencv
2 | First, using 'haarcascade_frontalface_alt.xml' to check if there is a face or not.  Second, using 'haarcascade_eye_tree_eyeglasses.xml' to check if there is a opened-eye or not. Thus, If I get data: face(o) -> eyes(x), that is the person who is closing his eyes.
3 | 


--------------------------------------------------------------------------------
/cv_close_eye_detect.py:
--------------------------------------------------------------------------------
 1 | import cv2
 2 | eye_cascPath = 'D:/DeepLearning/face/opencv-face-recognition-python-master/opencv-files/haarcascade_eye_tree_eyeglasses.xml'  #eye detect model
 3 | face_cascPath = 'D:/DeepLearning/face/opencv-face-recognition-python-master/opencv-files/haarcascade_frontalface_alt.xml'  #face detect model
 4 | faceCascade = cv2.CascadeClassifier(face_cascPath)
 5 | eyeCascade = cv2.CascadeClassifier(eye_cascPath)
 6 | 
 7 | cap = cv2.VideoCapture(0)
 8 | while 1:
 9 |     ret, img = cap.read()
10 |     if ret:
11 |         frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
12 |         # Detect faces in the image
13 |         faces = faceCascade.detectMultiScale(
14 |             frame,
15 |             scaleFactor=1.1,
16 |             minNeighbors=5,
17 |             minSize=(30, 30),
18 |             # flags = cv2.CV_HAAR_SCALE_IMAGE
19 |         )
20 |         # print("Found {0} faces!".format(len(faces)))
21 |         if len(faces) > 0:
22 |             # Draw a rectangle around the faces
23 |             for (x, y, w, h) in faces:
24 |                 cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
25 |             frame_tmp = img[faces[0][1]:faces[0][1] + faces[0][3], faces[0][0]:faces[0][0] + faces[0][2]:1, :]
26 |             frame = frame[faces[0][1]:faces[0][1] + faces[0][3], faces[0][0]:faces[0][0] + faces[0][2]:1]
27 |             eyes = eyeCascade.detectMultiScale(
28 |                 frame,
29 |                 scaleFactor=1.1,
30 |                 minNeighbors=5,
31 |                 minSize=(30, 30),
32 |                 # flags = cv2.CV_HAAR_SCALE_IMAGE
33 |             )
34 |             if len(eyes) == 0:
35 |                 print('no eyes!!!')
36 |             else:
37 |                 print('eyes!!!')
38 |             frame_tmp = cv2.resize(frame_tmp, (400, 400), interpolation=cv2.INTER_LINEAR)
39 |             cv2.imshow('Face Recognition', frame_tmp)
40 |         waitkey = cv2.waitKey(1)
41 |         if waitkey == ord('q') or waitkey == ord('Q'):
42 |             cv2.destroyAllWindows()
43 |             break
44 | 


--------------------------------------------------------------------------------