def detect_face(self, img, win):
dets = detector(img, 1)
if len(dets) == 0:
raise NoFaces()
largest_det = None
l_sq = None
for d in dets:
win.add_overlay(d)
sq = (d.right() - d.left()) * (d.top() - d.bottom())
sq = abs(sq)
if largest_det is None or sq > l_sq:
largest_det = d
l_sq = sq
d = largest_det
print("Detection: Left: {} Top: {} Right: {} Bottom: {}".format(
d.left(), d.top(), d.right(), d.bottom()))
# Get the landmarks/parts for the face in box d.
shape = sp(img, d)
# Draw the face landmarks on the screen so we can see what face is currently being processed.
win.add_overlay(shape, color=dlib.rgb_pixel(0, 255, 0))
face_descriptor = facerec.compute_face_descriptor(img, shape)
self.faces.append(img)
self.vecs.append(face_descriptor)
def show(self, out):
if not self.wi:
return
wi = self.wi
t, depthimage, colorimage, shape = out
wi.set_image(colorimage)
wi.clear_overlay()
self.framecount += 1
if shape is not None:
def topoint(dp):
return dlib.point(dp.x, dp.y)
if True:
fobp = dlib.full_object_detection(
shape.rect,
[topoint(shape.part(i)) for i in range(shape.num_parts)])
#for jj in range(fobp.num_parts):
if False:
p = fobp.part(jj)
if jj > self.framecount % 68:
break
self.wi.add_overlay_circle(dlib.dpoint(p.x, p.y),
2,
color=dlib.rgb_pixel(
255, 255, 0))
wi.add_overlay(fobp)
def see_coins(img_path, boxes, cols):
img = io.imread(img_path)
#draw each box
win = dlib.image_window()
win.set_image(img)
for i in np.arange(len(boxes)):
win.add_overlay(boxes[i], color=dlib.rgb_pixel(cols[i][0], cols[i][1], cols[i][2]))
#plt.figure()
#plt.imshow(img)
win.wait_until_closed()
def test_rgb_pixel():
p = rgb_pixel(0, 50, 100)
assert p.red == 0
assert p.green == 50
assert p.blue == 100
assert str(p) == "red: 0, green: 50, blue: 100"
assert repr(p) == "rgb_pixel(0,50,100)"
p = rgb_pixel(blue=0, red=50, green=100)
assert p.red == 50
assert p.green == 100
assert p.blue == 0
assert str(p) == "red: 50, green: 100, blue: 0"
assert repr(p) == "rgb_pixel(50,100,0)"
p.red = 100
p.green = 0
p.blue = 50
assert p.red == 100
assert p.green == 0
assert p.blue == 50
assert str(p) == "red: 100, green: 0, blue: 50"
assert repr(p) == "rgb_pixel(100,0,50)"
def test_rgb_pixel():
p = rgb_pixel(0, 50, 100)
assert p.red == 0
assert p.green == 50
assert p.blue == 100
assert str(p) == "red: 0, green: 50, blue: 100"
assert repr(p) == "rgb_pixel(0,50,100)"
p = rgb_pixel(blue=0, red=50, green=100)
assert p.red == 50
assert p.green == 100
assert p.blue == 0
assert str(p) == "red: 50, green: 100, blue: 0"
assert repr(p) == "rgb_pixel(50,100,0)"
p.red = 100
p.green = 0
p.blue = 50
assert p.red == 100
assert p.green == 0
assert p.blue == 50
assert str(p) == "red: 100, green: 0, blue: 50"
assert repr(p) == "rgb_pixel(100,0,50)"
def detect(self, file_):
self.file = file_
for img in self.file:
print('Processing image {}'.format(img))
img = dlib.load_rgb_image(img)
dets = self.detector(img, 1)
print('Number of faces detected: {}'.format(len(dets)))
self.win.clear_overlay()
self.win.set_image(img)
self.win.set_title('Number of faces detected: {}'.format(
len(dets)))
self.win.add_overlay(
dets,
color=dlib.rgb_pixel(0, 0, 255),
)
dlib.hit_enter_to_continue()
detector = dlib.simple_object_detector(detectors)
print("upsampling = ", detector.upsampling_amount)
detector.upsampling_amount = 1
#detector.save("combined_det.svm")
#detector = dlib.simple_object_detector('combined_det.svm')
detector_all = dlib.simple_object_detector('detector_all.svm')
#detector_all = dlib.simple_object_detector('detector.svm')
print("upsampling = ", detector.upsampling_amount)
win = dlib.image_window()
for f in sys.argv[1:]:
print(f)
img = dlib.load_rgb_image(f)
dets = detector(img, 2)
dets_all = detector_all(img, 2)
#dets, scores, idxs = dlib.simple_object_detector.run_multiple(detectors, img, 2)
# grow these rectangles slightly so they don't overlap dets in the image_window
dets_all = [dlib.grow_rect(d, 1) for d in dets_all]
win.clear_overlay()
win.set_image(img)
win.add_overlay(dets_all, dlib.rgb_pixel(0, 255, 0))
win.add_overlay(dets)
input("hit enter to continue")
# Create a HOG face detector using the built-in dlib class
face_detector = dlib.get_frontal_face_detector()
win = dlib.image_window()
# Load the image into an array
image = io.imread(file_name)
# Run the HOG face detector on the image data.
# The result will be the bounding boxes of the faces in our image.
detected_faces = face_detector(image, 1)
print("Found {} faces in the file {}".format(len(detected_faces), file_name))
# Open a window on the desktop showing the image
win.set_image(image)
# Loop through each face we found in the image
for i, face_rect in enumerate(detected_faces):
# Detected faces are returned as an object with the coordinates
# of the top, left, right and bottom edges
print("- Face #{} found at Left: {} Top: {} Right: {} Bottom: {}".format(
i, face_rect.left(), face_rect.top(), face_rect.right(),
face_rect.bottom()))
# Draw a box around each face we found
win.add_overlay(face_rect, dlib.rgb_pixel(0, 255, 0))
# Wait until the user hits <enter> to close the window
dlib.hit_enter_to_continue()
import sys
import cv2
import dlib
file = 'test.mp4'
cap = cv2.VideoCapture(file)
detector = dlib.get_frontal_face_detector()
win = dlib.image_window()
while True:
ret, frame = cap.read()
dets = detector(frame, 1)
print('Number of faces detected: {}'.format(len(dets)))
#for i, d in enumerate(dets):
# print('Detection {}: Left: {} Top: {} Right: {} Bottom: {}'.format(i, d.left(), d.top(), d.right(), d.bottom()))
win.clear_overlay()
win.set_image(frame)
win.set_title('Number of faces detected: {}'.format(len(dets)))
win.add_overlay(dets, color=dlib.rgb_pixel(255, 255, 0))
#for (w, y0, y1, x0, x1) in squares:
#shapes = dlib.full_object_detections()
#for idx, d in enumerate(dets):
if len(dets) == 0:
tracker = None
for d in dets:
if tracker is None:
tracker = dlib.correlation_tracker()
tracker.start_track(image, d)
win.add_overlay(d)
else:
tracker.update(image)
pos = tracker.get_position()
win.add_overlay(pos)
win.add_overlay(d, color=dlib.rgb_pixel(0, 255, 0))
#d.rectangle(((x0,y0),(x1,y1)), outline = (0, 255, 0))
#
#detd = dlib.rectangle(left=int(x0), top = int(y0), right = int(x1), bottom = int(y1))
#detd = d
#shape = face_pose_predictor(image, detd)
#shapes.append(face_pose_predictor(image, detd))
#win.add_overlay(shape)
#win.add_overlay(detd)
#facePred[0] = facerec.compute_face_descriptor(image, shape)
#if (clf.predict(facePred)==1):
#win.add_overlay(detd)
#arrayToSave.append(face_descriptor)
#print(face_descriptor)
#lmFaces.append(shape)
image_file = sys.argv[2]
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(predictor_path)
win = dlib.image_window()
print("Processing file: {}".format(image_file))
img = dlib.load_rgb_image(image_file)
win.clear_overlay()
win.set_image(img)
dets = detector(img, 2)
print("Number of faces detected: {}".format(len(dets)))
for index, det in enumerate(dets):
print("Detection {}: LEFT: {}, TOP: {}, RIGHT: {}, BOTTOM: {}".format(index, det.left(), det.top(), det.right(), det.bottom()))
shape = predictor(img, det)
# when you want to visualize divided landmarks
for marks, color in zip(landmarks , colors ):
for i in marks:
win.add_overlay_circle(shape.part(i), 1, dlib.rgb_pixel(color[2], color[1], color[0]))
# when you jush want to see whole landmarks
# win.add_overlay(shape)
win.add_overlay(dets)
dlib.hit_enter_to_continue()
for f in glob.glob(os.path.join(faces_folder_path, "*.jpg")):
print("Processing file: {}".format(f))
img = dlib.load_rgb_image(f)
win.clear_overlay()
win.set_image(img)
dets = detector(img, 1)
print("Number of faces detected: {}".format(len(dets)))
for k, d in enumerate(dets):
print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
k, d.left(), d.top(), d.right(), d.bottom()))
shape = predictor(img, d)
print("Part 0: {}, Part 1: {} ...".format(shape.part(0),
shape.part(1)))
for j in range(68):
x, y = shape.part(j).x, shape.part(j).y
win.add_overlay_circle(dlib.point(x, y), 1,
dlib.rgb_pixel(0, 0, 255))
win.add_overlay(shape)
win.add_overlay(dets)
dlib.hit_enter_to_continue()
def draw_face_landmarks(self,
image,
dets=None,
shapes=[],
return_drawn_landmarks=False,
draw_type="line"):
print("\nDrawing face landmarks..\n")
if not return_drawn_landmarks:
win = dlib.image_window()
win.set_image(image)
if self.sp == self.shape_68_face_landmarks:
face_landmarks_list = face_utils.FACIAL_LANDMARKS_68_IDXS
else:
face_landmarks_list = face_utils.FACIAL_LANDMARKS_5_IDXS
if image is None:
print("Please provide an image")
exit()
if dets is None:
dets = self.detect_face(image=image)
if len(shapes) == 0:
shapes = self.detect_face_landmarks(image=image, dets=dets)
# DOnly raw landmarks and display in dlib window if we are not returning the image
if not return_drawn_landmarks:
for shape in shapes:
win.add_overlay(shape, dlib.rgb_pixel(0, 255, 0))
# Draw landmarks over the image using opencv line or circle to return the drawn image
if return_drawn_landmarks:
for shape in shapes:
shape = face_utils.shape_to_np(shape)
# Loop over the face parts individually
for (name, (i, j)) in face_landmarks_list.items():
# Loop over the subset of facial landmarks, drawing the
# specific face part
px = None
py = None
for (x, y) in shape[i:j]:
if draw_type == "line":
if px is None and py is None:
px, py = x, y
cv2.line(image, (px, py), (x, y), (0, 255, 0), 2)
px, py = x, y
else:
cv2.circle(image, (x, y), 1, (0, 0, 255), -1)
return image
else:
dlib.hit_enter_to_continue()
return image
diff = round(calculate_diff(normal_image, restored), 3)
print(u'Восстановленное изображение отличается от оригинального '
u'на {p}%'.format(p=diff))
# Выполняем расчет и анализ антропометрических характеристик для
# исходного и реконструированного ИЛ
points, det = find_face_landmarks(normal_image)
points_rest, det_rest = find_face_landmarks(restored)
sum_distance = round(calculate_distance_between_landmarks(points, points_rest),
3)
print(u'Сумма Евклидовых расстояний между антропометрическими точками: '
u'{s}'.format(s=sum_distance))
diff = detect_antro_diff(points, points_rest)
columns = [
u'Высота лица', u'Ширина лица', u'Ширина глазной щели', u'Ширина носа',
u'Ширина губ', u'Высота носа', u'Высота от нижней губы до верхней'
]
rows = [u'Оригинал', u'Восстановленное', u'Разница', u'Разница %']
print(tabulate(diff, headers=columns, showindex=rows))
# Отображаем полученную антропометрику на исходном ИЛ для сравнения
# Создаем объект окна dlib
win = dlib.image_window()
win.set_title("Face landmarks")
win.clear_overlay()
win.set_image(normal_image)
# Исходные АПТ - синим цветом
win.add_overlay(det)
# АПТ реконструированного лица - красным цветом
win.add_overlay(det_rest, color=dlib.rgb_pixel(255, 0, 0))
win.wait_until_closed()
json.load(f))
testboxes.append(list(imgboxes))
idx = 0
print("Showing detections on the images in the faces folder...")
win = dlib.image_window()
print("Processing file: {}".format(f))
img = testimages[idx]
dets = detector(img)
# print(dets)
# print(boxes[0])
print("Number of faces detected: {}".format(len(dets)))
win.clear_overlay()
win.set_image(img)
win.add_overlay(dets)
color = dlib.rgb_pixel(0,255,0)
win.add_overlay(testboxes[idx], color=color)
dlib.hit_enter_to_continue()
# Next, suppose you have trained multiple detectors and you want to run them
# efficiently as a group. You can do this as follows:
detector1 = dlib.fhog_object_detector("detector.svm")
# In this example we load detector.svm again since it's the only one we have on
# hand. But in general it would be a different detector.
detector2 = dlib.fhog_object_detector("detector.svm")
# make a list of all the detectors you wan to run. Here we have 2, but you
# could have any number.
detectors = [detector1, detector2]
image = dlib.load_rgb_image(faces_folder + '/2008_002506.jpg')
[boxes, confidences, detector_idxs] = dlib.fhog_object_detector.run_multiple(detectors, image, upsample_num_times=1, adjust_threshold=0.0)
