def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
#CASE_PATH = ".\\pretrained_models\\haarcascade_frontalface_alt.xml"
count = 0
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
#count=0
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(
args.id_folder[0],
mtcnn,
sess,
embeddings,
images_placeholder,
phase_train_placeholder,
args.threshold,
)
test(mtcnn, id_data, args, sess, embeddings, images_placeholder,
phase_train_placeholder, count)
def init_tensor_flow(self):
print("Initializing Tensor-flow ...")
self.graph = tf.Graph()
self.sess = tf.Session()
print("Tensorflow session created ")
self.pnet, self.rnet, self.onet = detect_and_align.create_mtcnn(
self.sess, None)
print("Loading model file...")
# Load the model
self.load_model('./model/')
print("Model file loaded...")
self.images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
self.embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
self.phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
self.id_dataset = id_data.get_id_data('./ids/', self.pnet, self.rnet,
self.onet, self.sess,
self.embeddings,
self.images_placeholder,
self.phase_train_placeholder)
self.print_id_dataset_table()
def main(image_path, ready=False):
id_folder = ['ids']
test_folder = None
model = './model/'
with tf.Graph().as_default():
with tf.Session() as sess:
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
load_model(model)
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
id_dataset = id_data.get_id_data(id_folder[0], pnet, rnet, onet, sess, embeddings, images_placeholder, phase_train_placeholder)
print_id_dataset_table(id_dataset)
test_run(pnet, rnet, onet, sess, images_placeholder, phase_train_placeholder, embeddings, id_dataset, test_folder)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
if ready is False:
frame = cv2.imread(image_path)
elif ready is True:
frame = image_path
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(frame, pnet, rnet, onet)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
matching_id, dist = find_matching_id(id_dataset, embs[i, :])
if matching_id:
print('Hi %s! Distance: %1.4f' % (matching_id, dist))
else:
matching_id = 'Unknown'
print('Unkown! Couldn\'t fint match.')
return matching_id
else:
matching_id = 'Face Unfound'
print(matching_id)
return matching_id
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
print(np.array(embeddings).shape)
'''
def load_and_align_data(image_paths, image_size, margin, gpu_memory_fraction):
print('Creating networks and loading parameters')
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1.0)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
mtcnn = create_mtcnn(sess, None)
aligned_images = []
id_image_paths = []
id_names = []
for i in image_paths:
print(i)
img = misc.imread(os.path.expanduser(i), mode='RGB')
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face(img, mtcnn['pnet'], mtcnn['rnet'],
mtcnn['onet'])
if bounding_boxes.shape[0] > 0:
det = np.squeeze(bounding_boxes[0, 0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
prewhitened = prewhiten(aligned)
aligned_images.append(prewhitened)
id_image_paths += i
id_names += [i.split('/')[-2]]
print("Face recognized: ", id_names[-1])
images = np.stack(aligned_images)
return images, np.stack(id_names)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(
args.id_folder[0],
mtcnn,
sess,
embeddings,
images_placeholder,
phase_train_placeholder,
args.threshold,
)
print(id_data)
cap = cv2.VideoCapture(
'sample_fazen_hammad.mp4') #'sample1.mp4')#0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = True
show_id = True
show_fps = True
i = 0
while True:
start = time.time()
asb, frame = cap.read()
#cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
#asb, frame = cap.read()
#frame = cv2.resize(frame, (700,700), interpolation =cv2.INTER_NEAREST)
#frame=frame/255
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
#print(np.array(padded_bounding_boxes).shape,np.array(face_patches).shape)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print("Matches in frame:")
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = "Unknown"
print("Unknown! Couldn't fint match.")
faace = np.array(face_patches)
#faace=faace.reshape(faace.shape(-3),faace.shape(-2),faace.shape(-1))
faace = faace[0, :, :, :]
#print(faace.shape)
#cv2.imwrite("output/unknown"+str(i)+str(".png"),faace*255)
#i=i+1
else:
print("Hi %s! Distance: %1.4f" %
(matching_id, dist))
faace = np.array(face_patches)
faace = faace[0, :, :, :] #.reshape(160,160,3)
cv2.imwrite(
"output1/" + matching_id + str(i) + ".png",
faace * 255)
#i=i+1
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print("Couldn't find a face")
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
print("fps", fps, "seconds", seconds)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord("q"):
break
elif key == ord("l"):
show_landmarks = not show_landmarks
elif key == ord("b"):
show_bb = not show_bb
elif key == ord("i"):
show_id = not show_id
elif key == ord("f"):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(
sess, None
) #It calls create_mtcnn function from the detect_and_align file
load_model(
args.model
) #IT loads the facenet 20170512-110547.pb pre-trained model
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
#print("embeddings",embeddings)
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings,
images_placeholder, phase_train_placeholder,
args.threshold)
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = True
show_bb = True
show_id = True
show_fps = False
while (True):
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
print("landmarks", landmarks)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Unknown! Couldn\'t fint match.')
else:
print('Hi %s! Distance: %1.4f' %
(matching_id, dist))
now = datetime.now()
# print()
#time1=now.strftime("%I:%M:%S %p")
#writer = csv.writer(csvFile)
#writer.writerow(csvData)
#csvFile.close()
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame,
matching_id + now.strftime(" %I:%M%p"),
(bb[0], bb[3]), font, 1, (0, 0, 255),
2, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 1)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print('Couldn\'t find a face')
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
key = cv2.waitKey(100)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(
args.id_folder[0],
mtcnn,
sess,
embeddings,
images_placeholder,
phase_train_placeholder,
args.threshold,
)
# OPEN CAMERA AND TAKE A SNAPSHOT
cam = cv2.VideoCapture(0)
cv2.namedWindow("test")
img_counter = 0
while True:
ret, frame = cam.read()
cv2.imshow("test", frame)
if not ret:
break
k = cv2.waitKey(1)
if k % 256 == 27:
# ESC pressed
print("Escape hit, closing...")
break
elif k % 256 == 32:
# SPACE pressed
img_name = "attendance" + str(date.today()) + ".png"
cv2.imwrite(img_name, frame)
print("{} written!".format(img_name))
img_counter += 1
cam.release()
cv2.destroyAllWindows()
# Now that we have an image, we detect and recognise the faces and append them in list
present = []
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print("Attendance:")
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = "Unknown"
print("Unknown! Couldn't find match.")
else:
print("%s" % (matching_id)
) #prints all the names present in the image
present.append(matching_id)
with open('presentstudents.txt', 'w') as filehandle:
for listitem in present:
filehandle.write('%s\n' % listitem)
else:
print("Couldn't find a face")
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(
args.id_folder[0],
mtcnn,
sess,
embeddings,
images_placeholder,
phase_train_placeholder,
args.threshold,
)
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
while True:
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print("Matches in frame:")
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = "Unknown"
print("Unknown! Couldn't fint match.")
else:
print("Hi %s! Distance: %1.4f" %
(matching_id, dist))
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print("Couldn't find a face")
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord("q"):
break
elif key == ord("l"):
show_landmarks = not show_landmarks
elif key == ord("b"):
show_bb = not show_bb
elif key == ord("i"):
show_id = not show_id
elif key == ord("f"):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
faceCascade = cv2.CascadeClassifier(
'classifier/haarcascade_frontalface_default.xml')
file = os.path.join(os.getcwd(), "log.csv")
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
id_dataset = id_data.get_id_data(args.id_folder[0], pnet, rnet,
onet, sess, embeddings,
images_placeholder,
phase_train_placeholder)
print_id_dataset_table(id_dataset)
test_run(pnet, rnet, onet, sess, images_placeholder,
phase_train_placeholder, embeddings, id_dataset,
args.test_folder)
cap = cv2.VideoCapture(0)
cap.set(4, 9600)
cap.set(3, 12800)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
int_frame_height = int(frame_height)
# img_path = os.path.join(args.id_folder)
# f = open("D:\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\log.csv", 'a')
f = open(
"C:\\Users\\Siva-Datta.Mannava\\OneDrive - Shell\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\log.csv",
'a')
# df = pd.read_csv("D:\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\log.csv")
df = pd.read_csv(
"C:\\Users\\Siva-Datta.Mannava\\OneDrive - Shell\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\log.csv"
)
# df = pd.read_csv(f)
# print("df", df)
# columns = pd.read_csv("D:\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\log.csv", nrows = 0)
# print('columns', columns)
count = 0
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
total_people = 10
matched_ids = []
ids = os.listdir('ids')
while (True):
start = time.time()
_, frames = cap.read()
gray = cv2.cvtColor(frames, cv2.COLOR_BGR2GRAY)
count_msg = "Evacuated staff: " + str(count)
emergency_msg = "Emergency Evacuation"
remaining_msg = "Remaining staff: " + str(total_people - count)
cv2.putText(frames, emergency_msg, (0, 80),
cv2.FONT_HERSHEY_SIMPLEX, 3, (0, 0, 255), 3,
cv2.LINE_AA)
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.05,
minNeighbors=8,
minSize=(55, 55),
flags=cv2.CASCADE_SCALE_IMAGE)
imgs = []
if len(ids) < 5:
show_missing(frames, ids, 0, int_frame_height)
for (x, y, w, h) in faces:
crop_img = frames[y - 50:y + h + 25, x - 25:x + w + 25]
imgs.append(crop_img)
for frame in imgs:
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(
frame, pnet, rnet, onet)
id_dataset = id_data.get_id_data(args.id_folder[0], pnet,
rnet, onet, sess,
embeddings,
images_placeholder,
phase_train_placeholder)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
matching_id, dist = find_matching_id(
id_dataset, embs[i, :])
if matching_id:
print('Hi %s! Distance: %1.4f' %
(matching_id, dist))
if matching_id not in matched_ids:
matched_ids.append(matching_id)
count = count + 1
count_msg = "Evacuated staff: " + str(
count)
remaining_msg = "Remaining staff: " + str(
total_people - count)
if matching_id in ids:
ids.remove(matching_id)
else:
matching_id = 'Unkown'
print('Unkown! Couldn\'t fint match.')
'''Make folder and store the image'''
try:
# os.makedirs(os.path.join(args.id_folder, str(count)))
# dir1 = "D:\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\ids\\" + str(count)
dir1 = "C:\\Users\\Siva-Datta.Mannava\\OneDrive - Shell\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\ids\\" + str(
count)
os.makedirs(dir1)
except OSError as e:
if e.errno != errno.EEXIST:
raise
# path_img = "D:\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\ids\\" + str(count) + "\\"
path_img = "C:\\Users\\Siva-Datta.Mannava\\OneDrive - Shell\\Apps\\ml-comm\\smile\\facerecog\\FaceRecognition-master\\ids\\" + str(
count) + "\\"
img_name = path_img + str(count) + '.png'
cv2.imwrite(img_name, frame)
# start = time.time()
entry_time = datetime.datetime.fromtimestamp(
start).strftime('%c')
df_tmp = pd.DataFrame(
[[str(count), entry_time, "Still_Inside"]],
columns=df.columns)
count = count + 1
count_msg = "Evacuated staff: " + str(count)
remaining_msg = "Remaining staff: " + str(
total_people - count)
df = df.append(df_tmp)
df.to_csv(f, header=False, index=False)
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmarks[i, j]) - size,
int(landmarks[i, j + 5]) - size)
bottom_right = (int(landmarks[i, j]) + size,
int(landmarks[i, j + 5]) +
size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print('Couldn\'t find a face')
if len(ids) < 5:
show_missing(frames, ids, 0, int_frame_height)
cv2.putText(frames, remaining_msg, (0, int_frame_height - 15),
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 1,
cv2.LINE_AA)
cv2.putText(frames, count_msg, (0, 145),
cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 2,
cv2.LINE_AA)
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frames, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frames)
key = cv2.waitKey(1)
if key == ord('q'):
f.close()
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
max_step = -1
for f in files:
step_str = re.match(r'(^model-[\w\- ]+.ckpt-(\d+))', f)
if step_str is not None and len(step_str.groups()) >= 2:
step = int(step_str.groups()[1])
if step > max_step:
max_step = step
ckpt_file = step_str.groups()[0]
return meta_file, ckpt_file
with tf.Graph().as_default():
sess = tf.Session()
#with tf.Session() as sess:
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
model_exp = '/model'
print('Model directory: %s' % model_exp)
meta_file, ckpt_file = get_model_filenames(model_exp)
print('Metagraph file: %s' % meta_file)
print('Checkpoint file: %s' % ckpt_file)
saver = tf.train.import_meta_graph(os.path.join(model_exp, meta_file))
saver.restore(sess, os.path.join(model_exp, ckpt_file))
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name(
"phase_train:0")
def main(argv):
modelDir = os.path.join(fileDir, '..', '..', 'models')
parser = argparse.ArgumentParser()
parser.add_argument('--model',
type=str,
help="Path to Facenet pre-trained network model.",
default=os.path.join(
'./models/facenet-1/20170511-185253/',
'20170511-185253.pb'))
parser.add_argument('--imgDim',
type=int,
help="Default image dimension.",
default=96)
parser.add_argument('--identity',
type=str,
help="Identity of the person",
default='Unknown')
args = parser.parse_args(argv)
with tf.Graph().as_default():
with tf.Session() as sess:
pnet, rnet, onet = detect_and_align.create_mtcnn(
sess, args.identity)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
while (True):
start = time.time()
_, frame = cap.read()
matching_id, annotatedFrame = processFrame(
sess, frame, embeddings, None)
if matching_id:
cv2.imshow('frame', annotatedFrame)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(
args.id_folder[0],
mtcnn,
sess,
embeddings,
images_placeholder,
phase_train_placeholder,
args.threshold,
)
##Tao folder lưu hình ảnh của stranger trong video
flist = os.listdir('stranger')
folder_stranger = str(flist[len(flist) - 1])
if (folder_stranger != '0'):
folder_stranger = str(int(folder_stranger) + 1)
else:
folder_stranger = '1'
os.mkdir('.\\stranger\\' + folder_stranger)
if (args.link_video[0] == '0'):
cap = cv2.VideoCapture(0)
else:
cap = cv2.VideoCapture(args.link_video[0])
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
i = 0
tmp_time = time.time()
start_time = tmp_time
while True:
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print("Matches in frame:")
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
link_img = ''
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
link_img = ''
if matching_id is None:
matching_id = "Unknown"
print("Unknown! Couldn't fint match.")
if (args.link_video[0] != '0'): ##import video
link_img = './/stranger//' + folder_stranger + '//stranger_in_' + str(
i / cap.get(cv2.CAP_PROP_FPS)) + '.jpg'
else: ##live cam
link_img = './/stranger//' + folder_stranger + '//stranger_in_' + str(
round(-start_time + time.time())) + '.jpg'
else:
print("Hi %s! Distance: %1.4f" %
(matching_id, dist))
# if(args.link_video[0]!='0'):
# link_img='.//stranger//not_stranger_in_'+str(i/cap.get(cv2.CAP_PROP_FPS))+'.jpg'
# else:
# link_img='.//stranger//not_stranger_in_'+str(round(-start_time+time.time()))+'.jpg'
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
if (link_img != ''):
if (args.link_video[0] != '0'):
if (i % cap.get(cv2.CAP_PROP_FPS) == 0):
cv2.imwrite(link_img, frame)
else:
if (time.time() - tmp_time >= 1):
cv2.imwrite(link_img, frame)
tmp_time = time.time()
else:
print("Couldn't find a face")
i += 1
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord("q"):
break
elif key == ord("l"):
show_landmarks = not show_landmarks
elif key == ord("b"):
show_bb = not show_bb
elif key == ord("i"):
show_id = not show_id
elif key == ord("f"):
show_fps = not show_fps
mycmd_importcap.release()
cv2.destroyAllWindows()
def main(args):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Graph().as_default():
with tf.Session(config=config) as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder, float(args.threshold))
video = 'output1.avi'
gst_tx2 = "nvarguscamerasrc !video/x-raw(memory:NVMM), width=(int)640, height=(int)360, format=(string)I420, framerate=(fraction)30/1 ! nvvidconv flip-method=0 ! video/x-raw, format=(string)BGRx ! videoconvert ! video/x-raw, format=(string)BGR ! appsink"
gst_usb = "v4l2src device=/dev/video1 ! video/x-raw, width=(int)320, height=(int)240, format=(string)RGB ! videoconvert ! appsink"
cap = cv2.VideoCapture(gst_usb, cv2.CAP_GSTREAMER)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
present = defaultdict(int)
while (True):
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Unknown! Couldn\'t find match.')
else:
print('Hi %s! Distance: %1.4f' %
(matching_id, dist))
present[matching_id] += 1
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print('Couldn\'t find a face')
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('Frame', frame)
key = cv2.waitKey(1)
if key == ord('q'):
with open(
str(args.id_folder.split('/')[-1]) + '_' +
str(datetime.now()) + '.csv', 'w') as f:
writer = csv.writer(f)
writer.writerow([
'Class: ' + str(args.id_folder.split('/')[-1]) +
' ', 'Date and Time: ' + str(datetime.now())
])
for i in present.keys():
writer.writerow([i])
f.close()
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
sess.close()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.compat.v1.Session(
) as sess: #ch: tf.session wont work in tf2.0
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.compat.v1.get_default_graph(
).get_tensor_by_name("input:0")
embeddings = tf.compat.v1.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.compat.v1.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings,
images_placeholder, phase_train_placeholder,
args.threshold)
cap = cv2.VideoCapture(0, cv2.CAP_DSHOW)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
frame_detections = None
while True:
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
frame_detections = {
"embs": embs,
"bbs": padded_bounding_boxes,
"frame": frame.copy()
}
print("Matches in frame:")
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = "Unknown"
print("Unknown! Couldn't fint match.")
else:
# markAttendance(matching_id) #passing name to mark attendance
print("Hi %s! Distance: %1.4f" %
(matching_id, dist))
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print("Couldn't find a face")
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord("q"):
break
elif key == ord("l"):
show_landmarks = not show_landmarks
elif key == ord("b"):
show_bb = not show_bb
elif key == ord("i"):
show_id = not show_id
elif key == ord("f"):
show_fps = not show_fps
elif key == ord("s") and frame_detections is not None:
for emb, bb in zip(frame_detections["embs"],
frame_detections["bbs"]):
patch = frame_detections["frame"][bb[1]:bb[3],
bb[0]:bb[2], :]
cv2.imshow("frame", patch)
cv2.waitKey(1)
new_id = easygui.enterbox(
"Who's in the image? Leave empty for non-valid")
if len(new_id) > 0:
id_data.add_id(emb, new_id, patch)
cap.release()
cv2.waitKey(0)
cv2.destroyAllWindows()
def run():
with tf.Session() as sess:
LOG.log("Loading modell","SYSTEM")
#temp test
global pnet
global rnet
global onet
global images_placeholder
global embeddings
global phase_train_placeholder
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
model_exp = os.path.expanduser(model_path)
if (os.path.isfile(model_exp)):
# print('Model filename: %s' % model_exp)
with gfile.FastGFile(model_exp, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# set up tensorflow model
#load_model(model_path)
LOG.log("Start system","SYSTEM")
while True:
if cam_cap.isOpened():
start = time.time()
# Get current frame
global frame
ret, frame = cam_cap.read()
# Count tick
global ticks
ticks = ticks + 1
# Do detection
global DETECTION_SLEEP_TICKS
if DETECTION_SLEEP_TICKS <= ticks:
#print("Detection")
global face_box
global face_found
global show_id
global show_bb
global show_landmarks
# Do detection
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(frame, pnet, rnet, onet)
# if found faces
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
# print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmarks[i, j]) - size, int(landmarks[i, j + 5]) - size)
bottom_right = (int(landmarks[i, j]) + size, int(landmarks[i, j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
# Convert box to OpenCV
face_box = convert_tensorflow_box_to_openCV_box(padded_bounding_boxes[0])
# print (face_box)
# if running custom tracker this is needed
update_custom_tracker()
face_found = True
#return True
else:
# No face
face_found = False
#return False
# if face found
if face_found:
ticks = 0
global FAST_DETECTION_SLEEP_TICKS
DETECTION_SLEEP_TICKS = FAST_DETECTION_SLEEP_TICKS
else:
# Make less detections if not
ticks = 0
global SLOW_DETECTION_SLEEP_TICKS
DETECTION_SLEEP_TICKS = SLOW_DETECTION_SLEEP_TICKS
else:
# Do tracking
if face_found:
object_custom_tracking()
# print fps
end = time.time()
seconds = end - start
if seconds != 0:
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, 100), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
#Show Cam
cv2.imshow('Detection GUI', frame)
#Close Program functionallity
if cv2.waitKey(25) & 0xFF == ord('q'):
cam_cap.release()
cv2.destroyAllWindows()
break
time.sleep(0.2) # Sleep
def main(args):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Graph().as_default():
with tf.Session(config=config) as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings, images_placeholder, phase_train_placeholder, args.threshold)
# gst_usb ="v4l2src device=/dev/video1 ! video/x-raw, width=(int)320, height=(int)240, format=(string)RGB ! videoconvert ! appsink"
# cap = cv2.VideoCapture(gst_usb, cv2.CAP_GSTREAMER)
# frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = True
show_id = True
show_fps = True
i = 0 #Count for images
while(i < 1): #Recognition stops at last image
start = time.time()
# _, frame = cap.read() #Frame from video feed is deactivated
frame = cv2.imread('more_pics/pic{}.png'.format(i)) #Reads the images that are to be scanned by the FR model
frame_height = frame.shape[0] #Height of the image
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
matching_ids, matching_distances = id_data.find_matching_ids(embs)
for bb, landmark, matching_id, dist in zip(padded_bounding_boxes, landmarks, matching_ids, matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Unknown! Couldn\'t find match.')
else:
print('Hi %s! Distance: %1.4f' % (matching_id, dist))
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size, int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size, int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
else:
print('Couldn\'t find a face')
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
# cv2.imshow('frame', frame)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cv2.imwrite('more_pics/new{}.png'.format(i), frame) #Writes the image that was scanned
i += 1
# cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
id_dataset = id_data.get_id_data(args.id_folder[0], pnet, rnet, onet, sess, embeddings, images_placeholder, phase_train_placeholder)
print_id_dataset_table(id_dataset)
test_run(pnet, rnet, onet, sess, images_placeholder, phase_train_placeholder, embeddings, id_dataset, args.test_folder)
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT) # AREA TO BE EDITED
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
find_match = False
while(True):
start = time.time()
_, frame = cap.read()
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(frame, pnet, rnet, onet)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
matching_id, dist = find_matching_id(id_dataset, embs[i, :])
if matching_id:
print('Hi %s! Distance: %1.4f' %(matching_id, dist))
find_match = True
else:
matching_id = 'Unkown'
print('Unkown! Couldn\'t fint match.')
find_match = False
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmarks[i, j]) - size, int(landmarks[i, j + 5]) - size)
bottom_right = (int(landmarks[i, j]) + size, int(landmarks[i, j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
else:
print('Couldn\'t find a face')
if find_match is True:
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
def parse_arguments(argv):
parser = argparse.ArgumentParser()
parser.add_argument('model', type=str, help='Could be either a directory containing the meta_file and ckpt_file or a model protobuf (.pb) file')
parser.add_argument('id_folder', type=str, nargs='+', help='Folder containing ID folders')
parser.add_argument('--test_folder', type=str, help='Folder containing test images.', default=None)
return parser.parse_args(argv)
if __name__ == '__main__':
main(parse_arguments(sys.argv[1:]))
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings, images_placeholder, phase_train_placeholder, args.threshold)
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = False
show_fps = False
show_mesage = False
while(True):
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
matching_ids, matching_distances = id_data.find_matching_ids(embs)
for bb, landmark, matching_id, dist in zip(padded_bounding_boxes, landmarks, matching_ids, matching_distances):
if matching_id is None:
matching_id = 'Unknown'
createDefaultMessageONCE()
else:
createPersonalizedMessageONCE(matching_id)
#print('Hi %s! Distance: %1.4f' % (matching_id, dist))
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size, int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size, int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
else:
#print('Couldn\'t find a face')
noFaceMessageONCE()
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
#PYGAME loop
if g:
for event in pygame.event.get():
if event.type == QUIT or (event.type == KEYDOWN):
pygame.quit()
return
g.loop()
if show_fps:
print(str(fps))
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
#cv2.imshow('frame', frame)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
elif key == ord('m'):
show_mesage = not show_mesage
cap.release()
cv2.destroyAllWindows()
def gen1():
"""Video streaming generator function."""
print("Starting to generate frames!!!")
with tf.Graph().as_default():
with tf.Session() as sess:
print("Initialize tensor")
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
print("Loading model file...")
# Load the model
load_model('./model/')
print("Model file loaded...")
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
id_dataset = id_data.get_id_data('./ids/', pnet, rnet, onet, sess,
embeddings, images_placeholder,
phase_train_placeholder)
print_id_dataset_table(id_dataset)
while True:
frame = camera.get_frame()
print("Processing frame...")
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(
frame, pnet, rnet, onet)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
matching_id, dist = find_matching_id(
id_dataset, embs[i, :])
if matching_id:
print('Hi %s! Distance: %1.4f' %
(matching_id, dist))
else:
matching_id = 'Unkown'
print('Unkown! Couldn\'t fint match.')
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]), font,
1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]),
(255, 0, 0), 2)
else:
print("No face patches")
# cnt = cv2.imencode('.jpeg', frame)[1]
# b64 = base64.encodebytes(cnt)
encimg = cv2.imencode('.jpg', frame)[1].tostring()
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + encimg + b'\r\n')
def main(args):
print('################################################################################')
my_style_data=[]
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None) #It calls create_mtcnn function from the detect_and_align file
load_model(args.model) #IT loads the facenet 20170512-110547.pb pre-trained model
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings, images_placeholder, phase_train_placeholder, args.threshold)
#url ='rtsp://192.168.137.135:4747/video'
#cap = cv2.VideoCapture(0)
connection = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
connection.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
connection.settimeout(TIMEOUT_SOCKET)
connection.connect((IP_SERVER, PORT_SERVER))
while True:
try:
fileDescriptor = connection.makefile(mode='rb')
result = fileDescriptor.readline()
fileDescriptor.close()
result = base64.b64decode(result)
frame = np.fromstring(result, dtype=np.uint8)
frame_matrix = np.array(frame)
frame_matrix = np.reshape(frame_matrix, (IMAGE_HEIGHT, IMAGE_WIDTH,COLOR_PIXEL))
xyz=cv2.imshow('Window title', frame_matrix)
cv2.read(xyz)
print("cccc")
frame_height = frame_matrix.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = True
show_bb = True
show_id = True
show_fps = False
show_bb1 = True
while(True):
start = time.time()
v_offset = 50
time.sleep(0.0001)
_, frame = frame_matrix.read()
frame1=frame
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
matching_ids, matching_distances = id_data.find_matching_ids(embs)
for bb, landmark, matching_id, dist in zip(padded_bounding_boxes, landmarks, matching_ids, matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Unknown! Couldn\'t fint match.')
else:
#if(int(bb[0])<=170 and int(bb[3])<=357 and int(bb[2])<=437 and int(bb[1])<=164):
print('Hi akki %s! Distance: %1.4f' % (matching_id, dist))
now=datetime.now()
#csvData = [matching_id, dist,now.strftime("%x %I:%M:%S %p")]
'''with open('C:/myproject/Phase2-Copy_FaceRecognition-master/Student4.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()'''
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
print("bb_Frame",bb)
if(210<int(bb[0])<350 and 150<int(bb[1])<250 and 300<int(bb[2])<460 and 310<int(bb[3])<450):
welcome=" Welcome to Infogen labs"
cv2.putText(frame,matching_id+ welcome, (0, 50), font, 1, (0,0,255), 2, cv2.LINE_AA)
cv2.putText(frame,matching_id+now.strftime(" %I:%M%p"), (bb[0], bb[3]), font, 1, (0,0,255), 2, cv2.LINE_AA)
#csvData = [matching_id, dist,now.strftime("%x %I:%M:%S %p")]
def previous_and_next(some_iterable):
prevs, items, nexts = tee(some_iterable, 3)
prevs = chain([None], prevs)
nexts = chain(islice(nexts, 1, None), [None])
return zip(prevs, items, nexts)
csvData = [matching_id, dist,now.strftime("%x %I:%M:%S %p")]
with open('C:/myproject/1Copy_FaceRecognition-master - Copy/Student5.csv', 'a') as csvFile1:
writer = csv.writer(csvFile1)
writer.writerow(csvData)
csvFile1.close()
my_style_data.append(csvData)
print('******************************************************************************************')
print(my_style_data)
print('******************************************************************************************')
if len(my_style_data) >=7:
for prevs, item, nxt in previous_and_next(my_style_data):
try:
if prevs[0] != item[0] or item[0] != nxt[0]:
with open('C:/myproject/1Copy_FaceRecognition-master - Copy/Employee6.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(item)
csvFile.close()
except: pass
del(my_style_data[0:7])
'''if(matching_id=="Akshay"):
with open('C:/myproject/Phase2-Copy_FaceRecognition-master/Akshay.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()
if(matching_id=="Ajinkya"):
with open('C:/myproject/Phase2-Copy_FaceRecognition-master/Ajinkya.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()'''
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 1)
if show_bb1:
cv2.rectangle(frame1, (261,174),(457,380), (255,0,255),2)
if show_landmarks:
for j in range(5):
size = 1
x=(int(landmark[j]))
top_left = (int(landmark[j]) - size, int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size, int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
else:
print('Couldn\'t find a face')
cv2.imshow('frame', frame)
key = cv2.waitKey(100)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
frame_matrix.release()
cv2.destroyAllWindows()
def main():
# with tf.Graph().as_default():
with tf.Session() as sess:
pnet, rnet, onet = detect_and_align.create_mtcnn(sess, None)
#load_model('model/20170512-110547.pb')
#Load model
model_exp = os.path.expanduser('model/20170512-110547.pb')
if (os.path.isfile(model_exp)):
print('Model filename: %s' % model_exp)
with gfile.FastGFile(model_exp, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
# done loading
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name(
"phase_train:0")
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = True
show_bb = True
show_id = False
show_fps = True
while (True):
start = time.time()
_, frame = cap.read()
face_patches, padded_bounding_boxes, landmarks = detect_and_align.align_image(
frame, pnet, rnet, onet)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
for i in range(len(embs)):
bb = padded_bounding_boxes[i]
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]), font,
1, (255, 255, 255), 1, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]),
(255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmarks[i, j]) - size,
int(landmarks[i, j + 5]) - size)
bottom_right = (int(landmarks[i, j]) + size,
int(landmarks[i, j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print('Couldn\'t find a face')
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5), font,
1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
key = cv2.waitKey(1)
if key == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
def main(argv):
# parse inputs
parser = argparse.ArgumentParser()
parser.add_argument("input_file", help="Path to the input video.")
parser.add_argument("id_folder",
type=str,
nargs="+",
help="Folder containing ID folders")
args = parser.parse_args()
# initialize NSFW Model
model = OpenNsfwModel()
with tf.Graph().as_default():
with tf.Session() as sess:
# set variable defaults
videoFile = args.input_file
cap = cv2.VideoCapture(videoFile)
frameRate = cap.get(5) # get the frame rate
totalFrameCount = cap.get(7) # get the total number of frames
img_size = 64
margin = 0.4
frameNsfw = 0
isMinor = False
minorDetected = False
# set weights and initialize SFW model IsSFW
with tf.variable_scope('IsSFW'):
model.build(
weights_path="pretrained_models/open_nsfw-weights.npy")
fn_load_image = None
fn_load_image = create_yahoo_image_loader()
sess.run(tf.global_variables_initializer())
# initialize dlib face detector model and set variables
detector = dlib.get_frontal_face_detector()
model2 = WideResNet(img_size, 16, 8)()
model2.load_weights("pretrained_models/weights.29-3.76_utk.hdf5")
# initialize face identification model
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model("model/20170512-110547.pb")
threshold = 1.0
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs for face identification model
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings,
images_placeholder, phase_train_placeholder,
threshold)
while (cap.isOpened()):
ret, frame = cap.read()
frameId = cap.get(1) # get the current frame number
if (ret !=
True): # if there is no video frame detected then exit
break
# write video frame to disk and load as an image
cv2.imwrite('./temp_files/temp.jpg', frame)
image = fn_load_image('./temp_files/temp.jpg')
# determine SFW status
predictions = sess.run(model.predictions,
feed_dict={model.input: image})
if (predictions[0][1] >= 0.50):
frameNsfw = frameNsfw + 1
display_lbl = "NSFW"
AlertColor = [0, 0, 255]
else:
display_lbl = "SFW"
AlertColor = [255, 0, 0]
# detect faces in dlib face detection model
image2 = frame
image2_h, image2_w, _ = np.shape(image2)
detected = detector(image2, 0)
faces = np.empty((len(detected), img_size, img_size, 3))
if len(detected
) > 0: # one or more faces were found in the frame
for i, d in enumerate(detected):
# extract the coordinates of the face
x1, y1, x2, y2, w, h = d.left(), d.top(), d.right(
) + 1, d.bottom() + 1, d.width(), d.height()
xw1 = max(int(x1 - margin * w), 0)
yw1 = max(int(y1 - margin * h), 0)
xw2 = min(int(x2 + margin * w), image2_w - 1)
yw2 = min(int(y2 + margin * h), image2_h - 1)
# draw a rectangle around the face
cv2.rectangle(image2, (x1, y1), (x2, y2), (255, 0, 0),
2)
faces[i, :, :, :] = cv2.resize(
image2[yw1:yw2 + 1, xw1:xw2 + 1, :],
(img_size, img_size))
# determine the height of the rectangle in case is near top of frame
rectangle_height = y2 - y1
# predict ages and genders of faces using dlib model
results = model2.predict(faces)
predicted_genders = results[0]
ages = np.arange(0, 101).reshape(101, 1)
predicted_ages = results[1].dot(ages).flatten()
# draw predictions by faces using dlib model
for i, d in enumerate(detected):
isMinor = False
if (int(predicted_ages[i] < 18)
): # detect if a minor is present in the video
isMinor = True
minorDetected = True
label = "{},{},{}".format(
int(predicted_ages[i]),
"M" if predicted_genders[i][0] < 0.5 else "F",
"-MINOR" if isMinor else "")
draw_label(image2, (d.left(), d.top()), label,
rectangle_height)
# Locate faces and landmarks in frame for identification
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
font = cv2.FONT_HERSHEY_COMPLEX_SMALL
cv2.putText(frame, matching_id,
(bb[0] + 30, bb[3] + 5), font, 1,
(255, 0, 255), 1, cv2.LINE_AA)
# display whether frame is SFW or not
percentageComplete = round((frameId) / (totalFrameCount) * 100)
display_lbl = display_lbl + " " + str(
percentageComplete) + "% fps= " + str(round(frameRate, 2))
size = cv2.getTextSize(display_lbl, cv2.FONT_HERSHEY_SIMPLEX,
0.4, 1)[0]
cv2.rectangle(image2, (1, 15 - size[1]), (1 + size[0], 20),
AlertColor, cv2.FILLED)
cv2.putText(image2,
display_lbl, (1, 19),
cv2.FONT_HERSHEY_SIMPLEX,
0.4, (255, 255, 255),
1,
lineType=cv2.LINE_AA)
# display the frame as processed as quickly as possible
cv2.imshow('frame2', image2)
cv2.waitKey(1)
# end of video
cap.release()
cv2.destroyAllWindows()
if os.path.isfile('temp_files/temp.jpg'):
os.remove("temp_files/temp.jpg")
# print summary
if totalFrameCount > 0:
if (frameNsfw > 0):
if (minorDetected):
print("This video contains minors, and " +
str(round((frameNsfw / totalFrameCount * 100), 1)) +
"% of the video contains NSFW elements.")
else:
print(
str(round((frameNsfw / totalFrameCount * 100), 1)) +
"% of the video contains NSFW elements.")
else:
print("Video is SFW.")
else:
print(
"No video frames were detected! Please check the file type or file name."
)
def main(args):
# HOST='192.168.1.222'
# PORT=8485
# s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
# print('Socket created')
# s.bind((HOST,PORT))
# print('Socket bind complete')
# s.listen(10)
# print('Socket now listening')
# conn,addr=s.accept()
# data1 = b""
# payload_size = struct.calcsize(">L")
# print("payload_size: {}".format(payload_size))
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None) #It calls create_mtcnn function from the detect_and_align file
load_model(args.model) #IT loads the facenet 20170512-110547.pb pre-trained model
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings, images_placeholder, phase_train_placeholder, args.threshold)
#cap = cv2.VideoCapture(0)
#frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = True
show_bb = True
show_id = True
show_fps = False
show_bb1 = True
HOST='192.168.1.237'
PORT=8485
s=socket.socket(socket.AF_INET,socket.SOCK_STREAM)
print('Socket created')
s.bind((HOST,PORT))
print('Socket bind complete')
s.listen(10)
print('Socket now listening')
conn,addr=s.accept()
data1 = b""
payload_size = struct.calcsize(">L")
print("payload_size: {}".format(payload_size))
count=0
while(True):
while len(data1) < payload_size:
print("Recv: {}".format(len(data1)))
data1 += conn.recv(8046)
print("Done Recv: {}".format(len(data1)))
packed_msg_size = data1[:payload_size]
data1 = data1[payload_size:]
msg_size = struct.unpack(">L", packed_msg_size)[0]
#print("msg_size:{} {}".format(msg_size))
#count+=1
while len(data1) < msg_size:
data1 += conn.recv(8046)
frame_data = data1[:msg_size]
#print(frame_data)
data1 = data1[msg_size:]
frame=pickle.loads(frame_data, fix_imports=True, encoding="bytes")
frame = cv2.imdecode(frame, cv2.IMREAD_COLOR)
start = time.time()
# v_offset = 50
# _, frame = data1.read()
frame1=frame
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {images_placeholder: face_patches, phase_train_placeholder: False}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Matches in frame:')
matching_ids, matching_distances = id_data.find_matching_ids(embs)
for bb, landmark, matching_id, dist in zip(padded_bounding_boxes, landmarks, matching_ids, matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Unknown! Couldn\'t fint match.')
else:
#if(int(bb[0])<=170 and int(bb[3])<=357 and int(bb[2])<=437 and int(bb[1])<=164):
print('Hi akki %s! Distance: %1.4f' % (matching_id, dist))
now=datetime.now()
#time1=now.strftime("%I:%M:%S %p")
csvData = [matching_id, dist,now.strftime("%x %I:%M:%S %p")]
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
print("bb_Frame",bb)
if(210<int(bb[0])<350 and 150<int(bb[1])<250 and 300<int(bb[2])<460 and 310<int(bb[3])<450):
welcome=" Welcome to Infogen labs"
cv2.putText(frame,matching_id+ welcome, (0, 50), font, 1, (0,0,255), 2, cv2.LINE_AA)
cv2.putText(frame,matching_id+now.strftime(" %I:%M%p"), (bb[0], bb[3]), font, 1, (0,0,255), 2, cv2.LINE_AA)
csvData = [matching_id, dist,now.strftime("%x %I:%M:%S %p")]
with open('E:/clients/Face_Detection_&_RecognitionV2/Server-side-partV2/Student2.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()
'''if(matching_id=="Akshay"):
with open('C:/myproject/Phase2-Copy_FaceRecognition-master/Akshay.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()
if(matching_id=="Ajinkya"):
with open('C:/myproject/Phase2-Copy_FaceRecognition-master/Ajinkya.csv', 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(csvData)
csvFile.close()
'''
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]), (bb[2], bb[3]), (255, 0, 0), 1)
if show_bb1:
cv2.rectangle(frame1, (261,174),(457,380), (255,0,255),2)
if show_landmarks:
for j in range(5):
size = 1
x=(int(landmark[j]))
top_left = (int(landmark[j]) - size, int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size, int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right, (255, 0, 255), 2)
else:
print('Couldn\'t find a face')
end = time.time()
#seconds = end - start
#fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
key = cv2.waitKey(80)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
#cap.release()
cv2.destroyAllWindows()
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Setup models
mtcnn = detect_and_align.create_mtcnn(sess, None)
load_model(args.model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Load anchor IDs
id_data = IdData(args.id_folder[0], mtcnn, sess, embeddings,
images_placeholder, phase_train_placeholder,
args.threshold)
cap = cv2.VideoCapture(0)
frame_height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
show_landmarks = False
show_bb = False
show_id = True
show_fps = False
while (True):
def urljatayu():
aran = urllib.parse.quote(nama)
pintu = urllib.request.urlopen(
urllib.request.Request(
'http://jatayu.io/api/data/646ce982-de9b-11e9-8801-e4066d151e57/v1?value=1'
))
ket = urllib.request.urlopen(
urllib.request.Request(
'http://jatayu.io/api/data/646ce982-de9b-11e9-8801-e4066d151e57/v2?value=CAM'
))
saha = urllib.request.urlopen(
urllib.request.Request(
'http://jatayu.io/api/data/646ce982-de9b-11e9-8801-e4066d151e57/v3?value=%s'
% aran))
print("Membuka pintu")
start = time.time()
_, frame = cap.read()
# Locate faces and landmarks in frame
face_patches, padded_bounding_boxes, landmarks = detect_and_align.detect_faces(
frame, mtcnn)
if len(face_patches) > 0:
face_patches = np.stack(face_patches)
feed_dict = {
images_placeholder: face_patches,
phase_train_placeholder: False
}
embs = sess.run(embeddings, feed_dict=feed_dict)
print('Wajah terdeteksi:')
matching_ids, matching_distances = id_data.find_matching_ids(
embs)
for bb, landmark, matching_id, dist in zip(
padded_bounding_boxes, landmarks, matching_ids,
matching_distances):
if matching_id is None:
matching_id = 'Unknown'
print('Tidak dikenal! Tidak ada wajah yang cocok.')
cv2.putText(frame, "Akses Ditolak ", (50, 50),
cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 0, 255), 2, cv2.LINE_AA)
else:
print('Sampurasun %s! Jarak: %1.4f' %
(matching_id, dist))
global dikenal
dikenal = True
cv2.putText(frame, "Akses Diterima ", (50, 50),
cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 255, 0), 2, cv2.LINE_AA)
#ganti "_" jadi " "
namanya = matching_id.split("_")
nama = (' '.join(namanya))
if show_id:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, matching_id, (bb[0], bb[3]),
font, 1, (158, 126, 0), 2, cv2.LINE_AA)
if show_bb:
cv2.rectangle(frame, (bb[0], bb[1]),
(bb[2], bb[3]), (255, 0, 0), 2)
if show_landmarks:
for j in range(5):
size = 1
top_left = (int(landmark[j]) - size,
int(landmark[j + 5]) - size)
bottom_right = (int(landmark[j]) + size,
int(landmark[j + 5]) + size)
cv2.rectangle(frame, top_left, bottom_right,
(255, 0, 255), 2)
else:
print('Tidak ada wajah terdeteksi')
if (dikenal):
print("mengirim ke jatayu")
urljatayu()
dikenal = False
end = time.time()
seconds = end - start
fps = round(1 / seconds, 2)
if show_fps:
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(frame, str(fps), (0, int(frame_height) - 5),
font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.imshow('frame', frame)
cv2.namedWindow("frame", cv2.WND_PROP_FULLSCREEN)
cv2.setWindowProperty("frame", cv2.WND_PROP_FULLSCREEN,
cv2.WINDOW_FULLSCREEN)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('l'):
show_landmarks = not show_landmarks
elif key == ord('b'):
show_bb = not show_bb
elif key == ord('i'):
show_id = not show_id
elif key == ord('f'):
show_fps = not show_fps
cap.release()
cv2.destroyAllWindows()
