def predict_image():
"""Gets an image file via POST request, feeds the image to the FaceNet model, the resulting embedding is then
sent to be compared with the embeddings database. The image file is not stored.
An html page is then rendered showing the prediction result.
"""
if request.method == 'POST':
if 'file' not in request.files:
return "No file part"
file = request.files['file']
filename = file.filename
if filename == "":
return "No selected file"
if file and allowed_file(filename=filename, allowed_set=allowed_set):
# Read image file as numpy array of RGB dimension
img = imread(name=file, mode='RGB')
# Detect and crop a 160 x 160 image containing a human face in the image file
img = get_face(img=img,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
# If a human face is detected
if img is not None:
embedding = forward_pass(
img=img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
embedding_dict = load_embeddings()
if embedding_dict:
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(embedding=embedding,
embedding_dict=embedding_dict)
return render_template('predict_result.html',
identity=identity)
else:
return render_template(
'predict_result.html',
identity=
"No embedding files detected! Please upload image files for embedding!"
)
else:
return render_template(
'predict_result.html',
identity=
"Operation was unsuccessful! No human face was detected.")
else:
return "POST HTTP method required!"
def get_frame(self):
success, frame_orig = self.video.read()
# We are using Motion JPEG, but OpenCV defaults to capture raw images,
# so we must encode it into JPEG in order to correctly display the
# video stream.
# faces = face_cascade.detectMultiScale(image, 1.3, 5)
frame = cv2.resize(src=frame_orig, dsize=(0, 0), fx=0.5, fy=0.5)
embedding_dict = load_embeddings()
frame = frame[:, :, ::-1]
if frame.size > 0:
faces, rects = get_faces_live(img=frame,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
# If there are human faces detected
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
# Scale coordinates of face locations by the resize ratio
rect = [coordinate * 2 for coordinate in rect]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(embedding=face_embedding,
embedding_dict=embedding_dict)
cv2.rectangle(img=frame_orig,
pt1=(rect[0], rect[1]),
pt2=(rect[2], rect[3]),
color=(255, 215, 0),
thickness=2)
W = int(rect[2] - rect[0]) // 2
cv2.putText(img=frame_orig,
text=identity,
org=(rect[0] + W - (W // 2), rect[1] - 7),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.5,
color=(255, 215, 0),
thickness=1,
lineType=cv2.LINE_AA)
ret, jpeg = cv2.imencode('.jpg', frame_orig)
return jpeg.tobytes()
def predict_image(file):
# file = request.files['file']
# file = os.path.join(APP_ROOT, 'uploads/Abdulrahman Safh.png')
# Read image file as numpy array of RGB dimension
#img = io.imread(fname=file)
img = imread(name=file, mode='RGB')
# Detect and crop a 160 x 160 image containing a human face in the image file
faces, rects = get_faces_live(img=img, pnet=pnet, rnet=rnet,
onet=onet, image_size=image_size)
#global d
# If there are human faces detected
if faces:
embedding_dict = load_embeddings()
if embedding_dict:
people_found = []
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
face_embedding = forward_pass(
img=face_img, session=facenet_persistent_session,
images_placeholder=images_placeholder, embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size
)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(
embedding=face_embedding, embedding_dict=embedding_dict)
people_found.append(identity)
cv2.rectangle(img, (rect[0], rect[1]), (rect[2], rect[3]), (0, 255, 0), 3)
W = int(rect[2] - rect[0]) // 2
H = int(rect[3] - rect[1]) // 2
cv2.putText(img, identity, (rect[0] + W - (W // 2), rect[1] - 7),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 255), 1, cv2.LINE_AA)
# code for saving the output images
# cv2.imwrite("SavedImgesFull/file_%d.jpg" % d, img)
#d += 1
return people_found
else:
# return ["No Face"]
return None
# return render_template(
# 'predict_result.html',
# identity="No embedding files detected! Please upload image files for embedding!"
# )
else:
# return ["No Image"]
return None
def face_detect_live():
"""Detects faces in real-time via Web Camera."""
embedding_dict = load_embeddings()
if embedding_dict:
try:
# Start non-blocking multi-threaded OpenCV video stream
cap = WebcamVideoStream(src=0).start()
while True:
frame_orig = cap.read() # Read frame
# Resize frame to half its size for faster computation
frame = cv2.resize(src=frame_orig,
dsize=(0, 0),
fx=0.5,
fy=0.5)
# Convert the image from BGR color (which OpenCV uses) to RGB color
frame = frame[:, :, ::-1]
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if frame.size > 0:
faces, rects = get_faces_live(img=frame,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
# If there are human faces detected
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
# Scale coordinates of face locations by the resize ratio
rect = [coordinate * 2 for coordinate in rect]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(
embedding=face_embedding,
embedding_dict=embedding_dict)
cv2.rectangle(img=frame_orig,
pt1=(rect[0], rect[1]),
pt2=(rect[2], rect[3]),
color=(255, 215, 0),
thickness=2)
W = int(rect[2] - rect[0]) // 2
cv2.putText(img=frame_orig,
text=identity,
org=(rect[0] + W - (W // 2),
rect[1] - 7),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.5,
color=(255, 215, 0),
thickness=1,
lineType=cv2.LINE_AA)
cv2.imshow(winname='Video', mat=frame_orig)
# Keep showing camera stream even if no human faces are detected
cv2.imshow(winname='Video', mat=frame_orig)
else:
continue
cap.stop() # Stop multi-threaded Video Stream
cv2.destroyAllWindows()
return render_template(template_name_or_list='index.html')
except Exception as e:
print(e)
else:
return render_template(
template_name_or_list="warning.html",
status=
"No embedding files detected! Please upload image files for embedding!"
)
def face_detect_live():
"""Detects faces in real-time via Web Camera."""
embedding_dict = load_embeddings()
if embedding_dict:
try:
cap = cv2.VideoCapture(0)
while True:
cap.grab() # For use in multi-camera environments when the cameras do not have hardware synchronization
return_code, frame_orig = cap.read() # Read frame
# Resize frame to half its size for faster computation
frame = cv2.resize(frame_orig, (0, 0), fx=0.5, fy=0.5)
# Convert the image from BGR color (which OpenCV uses) to RGB color
frame = frame[:, :, ::-1]
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if frame.size > 0:
faces, rects = get_faces_live(img=frame, pnet=pnet, rnet=rnet, onet=onet, image_size=image_size)
# If there are human faces detected
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
# Scale coordinates of face locations by the resize ratio
rect = [coordinate * 2 for coordinate in rect]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size
)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(embedding=face_embedding, embedding_dict=embedding_dict)
cv2.rectangle(frame_orig, (rect[0], rect[1]), (rect[2], rect[3]), (255, 215, 0), 2)
W = int(rect[2] - rect[0]) // 2
H = int(rect[3] - rect[1]) // 2
cv2.putText(frame_orig, identity, (rect[0]+W-(W//2), rect[1]-7),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 215, 0), 1, cv2.LINE_AA)
cv2.imshow('Video', frame_orig)
# Keep showing camera stream even if no human faces are detected
cv2.imshow('Video', frame_orig)
else:
continue
cap.release()
cv2.destroyAllWindows()
return render_template('index.html')
except Exception as e:
print(e)
else:
return render_template(
"warning.html",
status="No embedding files detected! Please upload image files for embedding!"
)
def get_frame():
embedding_dict = load_embeddings()
if embedding_dict:
try:
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 500)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 500)
while True:
#get camera frame
ret, frame = cap.read() # Read frame
#print(frame)
# Resize frame to half its size for faster computation
frame = cv2.resize(src=frame, dsize=(0, 0), fx=0.8, fy=0.8)
# Convert the image from BGR color (which OpenCV uses) to RGB color
#frame = frame[:, :, ::-1]
#if cv2.waitKey(1) & 0xFF == ord('q'):
# break
#
if frame.size > 0:
faces, rects = get_faces_live(img=frame,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
# Scale coordinates of face locations by the resize ratio
rect = [coordinate for coordinate in rect]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(
embedding=face_embedding,
embedding_dict=embedding_dict)
cv2.rectangle(img=frame,
pt1=(rect[0], rect[1]),
pt2=(rect[2], rect[3]),
color=(0, 0, 255),
thickness=2)
W = int(rect[2] - rect[0]) // 2
cv2.putText(img=frame,
text=identity,
org=(rect[0] + W - (W // 2),
rect[1] - 7),
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.5,
color=(0, 0, 255),
thickness=1,
lineType=cv2.LINE_AA)
ret, jpeg = cv2.imencode('.jpg', frame)
ret, jpeg = cv2.imencode('.jpg', frame)
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' +
jpeg.tobytes() + b'\r\n\r\n')
else:
continue
except Exception as e:
print(e)
def face_detect_live():
"""Detects faces in real-time via Web Camera."""
embedding_dict = load_embeddings()
if embedding_dict:
try:
cap = cv2.VideoCapture(0)
while True:
return_code, frame = cap.read() # RGB frame
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if frame.size > 0:
faces, rects = get_faces_live(img=frame,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
# If there are human faces detected
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(
embedding=face_embedding,
embedding_dict=embedding_dict)
cv2.rectangle(frame, (rect[0], rect[1]),
(rect[2], rect[3]), (255, 215, 0), 2)
W = int(rect[2] - rect[0]) // 2
H = int(rect[3] - rect[1]) // 2
cv2.putText(frame, identity,
(rect[0] + W - (W // 2), rect[1] - 7),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 215, 0), 1, cv2.LINE_AA)
cv2.imshow('Video', frame)
# Keep showing camera stream even if no human faces are detected
cv2.imshow('Video', frame)
else:
continue
cap.release()
cv2.destroyAllWindows()
return render_template('index.html')
except Exception as e:
print(e)
else:
return "No embedding files detected! Please upload image files for embedding!"
def face_detect_live():
# Load text reading engine
#engine = pyttsx3.init()
spoken_face_names = []
greetings = [
'How do you do', 'Hello', 'Hi', 'Hai', 'Hey', 'How have you been',
'How are you', 'How is it going', 'Salam alikom ', 'Esh loonak ya',
'Ahlaaaan'
]
embedding_dict = load_embeddings()
if embedding_dict:
try:
cap = cv2.VideoCapture(0)
while True:
return_code, frame = cap.read() # RGB frame
if cv2.waitKey(1) & 0xFF == ord('q'):
break
faces, rects = get_faces_live(img=frame,
pnet=pnet,
rnet=rnet,
onet=onet,
image_size=image_size)
# If there are human faces detected
if faces:
for i in range(len(faces)):
face_img = faces[i]
rect = rects[i]
face_embedding = forward_pass(
img=face_img,
session=facenet_persistent_session,
images_placeholder=images_placeholder,
embeddings=embeddings,
phase_train_placeholder=phase_train_placeholder,
image_size=image_size)
# Compare euclidean distance between this embedding and the embeddings in 'embeddings/'
identity = identify_face(embedding=face_embedding,
embedding_dict=embedding_dict)
cv2.rectangle(frame, (rect[0], rect[1]),
(rect[2], rect[3]), (255, 215, 0), 2)
W = int(rect[2] - rect[0]) // 2
H = int(rect[3] - rect[1]) // 2
cv2.putText(frame, identity,
(rect[0] + W - (W // 2), rect[1] - 7),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 215, 0), 1, cv2.LINE_AA)
if identity == "Unknown":
continue
elif identity in spoken_face_names:
continue
else:
print(random.choice(greetings) + " " + identity)
#engine.say(random.choice(greetings) + name)
#engine.runAndWait()
spoken_face_names.append(identity)
continue
cv2.imshow('Video', frame)
else:
continue
cap.release()
cv2.destroyAllWindows()
return render_template('index.html')
except Exception as e:
print(e)
else:
return "No loaded faces detected! Please upload image files for embedding!"
