-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathFace_mesh.py
236 lines (189 loc) · 8.34 KB
/
Face_mesh.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
import cv2 as cv
import cv2
import mediapipe as mp
import time
import utils, math
import numpy as np
import pyautogui
#dimention
width = 500
height = 500
# variables
frame_counter =0
CEF_COUNTER =0
TOTAL_BLINKS =0
# constants
CLOSED_EYES_FRAME =3
FONTS =cv.FONT_HERSHEY_COMPLEX
# face bounder indices
FACE_OVAL=[ 10, 338, 297, 332, 284, 251, 389, 356, 454, 323, 361, 288, 397, 365, 379, 378, 400, 377, 152, 148, 176, 149, 150, 136, 172, 58, 132, 93, 234, 127, 162, 21, 54, 103,67, 109]
# lips indices for Landmarks
LIPS=[ 61, 146, 91, 181, 84, 17, 314, 405, 321, 375,291, 308, 324, 318, 402, 317, 14, 87, 178, 88, 95,185, 40, 39, 37,0 ,267 ,269 ,270 ,409, 415, 310, 311, 312, 13, 82, 81, 42, 183, 78 ]
LOWER_LIPS =[61, 146, 91, 181, 84, 17, 314, 405, 321, 375, 291, 308, 324, 318, 402, 317, 14, 87, 178, 88, 95]
UPPER_LIPS=[ 185, 40, 39, 37,0 ,267 ,269 ,270 ,409, 415, 310, 311, 312, 13, 82, 81, 42, 183, 78]
# Left eyes indices
LEFT_EYE =[ 362, 382, 381, 380, 374, 373, 390, 249, 263, 466, 388, 387, 386, 385,384, 398 ]
LEFT_EYEBROW =[ 336, 296, 334, 293, 300, 276, 283, 282, 295, 285 ]
# right eyes indices
RIGHT_EYE=[ 33, 7, 163, 144, 145, 153, 154, 155, 133, 173, 157, 158, 159, 160, 161 , 246 ]
RIGHT_EYEBROW=[ 70, 63, 105, 66, 107, 55, 65, 52, 53, 46 ]
map_face_mesh = mp.solutions.face_mesh
# camera object
camera = cv.VideoCapture(0)
# landmark detection function
def landmarksDetection(img, results, draw=False):
img_height, img_width= img.shape[:2]
# list[(x,y), (x,y)....]
mesh_coord = [(int(point.x * img_width), int(point.y * img_height)) for point in results.multi_face_landmarks[0].landmark]
if draw :
[cv.circle(img, p, 2, (0,255,0), -1) for p in mesh_coord]
# returning the list of tuples for each landmarks
return mesh_coord
# Euclaidean distance
def euclaideanDistance(point, point1):
x, y = point
x1, y1 = point1
distance = math.sqrt((x1 - x)**2 + (y1 - y)**2)
return distance
# Blinking Ratio
def blinkRatio(img, landmarks, right_indices, left_indices):
# Right eyes
# horizontal line
rh_right = landmarks[right_indices[0]]
rh_left = landmarks[right_indices[8]]
# vertical line
rv_top = landmarks[right_indices[12]]
rv_bottom = landmarks[right_indices[4]]
# draw lines on right eyes
cv.line(img, rh_right, rh_left, utils.GREEN, 2)
cv.line(img, rv_top, rv_bottom, utils.WHITE, 2)
# LEFT_EYE
# horizontal line
lh_right = landmarks[left_indices[0]]
lh_left = landmarks[left_indices[8]]
# vertical line
lv_top = landmarks[left_indices[12]]
lv_bottom = landmarks[left_indices[4]]
cv.line(img, lh_right, lh_left, utils.GREEN, 2)
cv.line(img, lv_top, lv_bottom, utils.WHITE, 2)
rhDistance = euclaideanDistance(rh_right, rh_left)
rvDistance = euclaideanDistance(rv_top, rv_bottom)
lvDistance = euclaideanDistance(lv_top, lv_bottom)
lhDistance = euclaideanDistance(lh_right, lh_left)
reRatio = rhDistance/rvDistance
leRatio = lhDistance/lvDistance
ratio = (reRatio+leRatio)/2
return ratio
# Eyes Extrctor function,
def eyesExtractor(img, right_eye_coords, left_eye_coords):
# converting color image to scale image
gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
# getting the dimension of image
dim = gray.shape
# creating mask from gray scale dim
mask = np.zeros(dim, dtype=np.uint8)
# drawing Eyes Shape on mask with white color
cv.fillPoly(mask, [np.array(right_eye_coords, dtype=np.int32)], 255)
cv.fillPoly(mask, [np.array(left_eye_coords, dtype=np.int32)], 255)
# showing the mask
# cv.imshow('mask', mask)
# draw eyes image on mask, where white shape is
eyes = cv.bitwise_and(gray, gray, mask=mask)
# change black color to gray other than eys
# cv.imshow('eyes draw', eyes)
eyes[mask==0]=155
# getting minium and maximum x and y for right and left eyes
# For Right Eye
r_max_x = (max(right_eye_coords, key=lambda item: item[0]))[0]
r_min_x = (min(right_eye_coords, key=lambda item: item[0]))[0]
r_max_y = (max(right_eye_coords, key=lambda item : item[1]))[1]
r_min_y = (min(right_eye_coords, key=lambda item: item[1]))[1]
# For LEFT Eye
l_max_x = (max(left_eye_coords, key=lambda item: item[0]))[0]
l_min_x = (min(left_eye_coords, key=lambda item: item[0]))[0]
l_max_y = (max(left_eye_coords, key=lambda item : item[1]))[1]
l_min_y = (min(left_eye_coords, key=lambda item: item[1]))[1]
# croping the eyes from mask
cropped_right = eyes[r_min_y: r_max_y, r_min_x: r_max_x]
cropped_left = eyes[l_min_y: l_max_y, l_min_x: l_max_x]
# returning the cropped eyes
return cropped_right, cropped_left
# Eyes Postion Estimator
def positionEstimator(cropped_eye):
# getting height and width of eye
h, w =cropped_eye.shape
# remove the noise from images
gaussain_blur = cv.GaussianBlur(cropped_eye, (9,9),0)
median_blur = cv.medianBlur(gaussain_blur, 3)
# applying thrsholding to convert binary_image
ret, threshed_eye = cv.threshold(median_blur, 130, 255, cv.THRESH_BINARY)
# create fixd part for eye with
piece = int(w/3)
# slicing the eyes into three parts
right_piece = threshed_eye[0:h, 0:piece]
center_piece = threshed_eye[0:h, piece: piece+piece]
left_piece = threshed_eye[0:h, piece +piece:w]
# calling pixel counter function
eye_position, color = pixelCounter(right_piece, center_piece, left_piece)
return eye_position, color
# creating pixel counter function
def pixelCounter(first_piece, second_piece, third_piece):
# counting black pixel in each part
right_part = np.sum(first_piece==0)
center_part = np.sum(second_piece==0)
left_part = np.sum(third_piece==0)
# creating list of these values
eye_parts = [right_part, center_part, left_part]
# getting the index of max values in the list
max_index = eye_parts.index(max(eye_parts))
pos_eye =''
if max_index==0:
pos_eye="RIGHT"
color=[utils.BLACK, utils.GREEN]
elif max_index==1:
pos_eye = 'CENTER'
color = [utils.YELLOW, utils.PINK]
elif max_index ==2:
pos_eye = 'LEFT'
color = [utils.GRAY, utils.YELLOW]
pyautogui.press('tab')
time.sleep(1.5)
else:
pos_eye="Closed"
color = [utils.GRAY, utils.YELLOW]
return pos_eye, color
with map_face_mesh.FaceMesh(min_detection_confidence =0.5, min_tracking_confidence=0.5) as face_mesh:
# starting Video loop here.
while True:
ret, frame = camera.read() # getting frame from camera
if not ret:
break # no more frames break
# resizing frame
frame = cv.resize(frame, None, fx=1.5, fy=1.5, interpolation=cv.INTER_CUBIC)
frame_height, frame_width= frame.shape[:2]
rgb_frame = cv.cvtColor(frame, cv.COLOR_RGB2BGR)
results = face_mesh.process(rgb_frame)
if results.multi_face_landmarks:
mesh_coords = landmarksDetection(frame, results, False)
ratio = blinkRatio(frame, mesh_coords, RIGHT_EYE, LEFT_EYE)
# cv.putText(frame, f'ratio {ratio}', (100, 100), FONTS, 1.0, utils.GREEN, 2)
# utils.colorBackgroundText(frame, f'Ratio : {round(ratio,2)}', FONTS, 0.7, (30,100),2, utils.PINK, utils.YELLOW)
if ratio > 4.5 :
pyautogui.press('enter')
cv.polylines(frame, [np.array([mesh_coords[p] for p in LEFT_EYE ], dtype=np.int32)], True, utils.GREEN, 1, cv.LINE_AA)
cv.polylines(frame, [np.array([mesh_coords[p] for p in RIGHT_EYE ], dtype=np.int32)], True, utils.GREEN, 1, cv.LINE_AA)
# Blink Detector Counter Completed
right_coords = [mesh_coords[p] for p in RIGHT_EYE]
left_coords = [mesh_coords[p] for p in LEFT_EYE]
crop_right, crop_left = eyesExtractor(frame, right_coords, left_coords)
# cv.imshow('right', crop_right)
# cv.imshow('left', crop_left)
eye_position, color = positionEstimator(crop_right)
eye_position_left, color = positionEstimator(crop_left)
resized_image = cv2.resize(frame, (width, height))
cv.imshow('frame', resized_image)
key = cv.waitKey(2)
if key==ord('q') or key ==ord('Q'):
break
cv.destroyAllWindows()
camera.release()