def match(clf, filename):
# Load the test image with unknown faces into a numpy array
test_image = face_recognition.load_image_file(filename)
# Find all the faces in the test image using the default HOG-based model
face_locations = face_recognition.face_locations(test_image)
no = len(face_locations)
print("\nNumber of faces detected: ", no)
# Predict all the faces in the test image using the trained classifier
firstname = None
print("\n(☞ﾟヮﾟ)☞ ☜(ﾟヮﾟ☜)\n")
print("Found:")
for i in range(no):
test_image_enc = face_recognition.face_encodings(test_image)[i]
name = clf.predict([test_image_enc])
probs = clf.predict_proba([test_image_enc])
print(*name)
firstname = (str(name[0]))
return (firstname, no)
def train():
# Training the SVC classifier
# The training data would be all the face encodings from all the known images and the labels are their names
encodings = []
names = []
# Training directory
train_dir = os.listdir("train_dir/")
# Loop through each person in the training directory
for person in train_dir:
pix = os.listdir("train_dir/" + person)
# pix = [item for item in pix if not item.startswith('.') and os.path.isfile(os.path.join(root, item))]
# Loop through each training image for the current person
for person_img in pix:
# Get the face encodings for the face in each image file
if person_img == ".DS_Store":
continue
face = face_recognition.load_image_file(
"train_dir/" + person + "/" + person_img
)
face_bounding_boxes = face_recognition.face_locations(face)
if len(face_bounding_boxes) == 1:
face_enc = face_recognition.face_encodings(face)[0]
# Add face encoding for current image with corresponding label (name) to the training data
encodings.append(face_enc)
names.append(person)
# Create and train the SVC classifier
clf = svm.SVC(gamma="scale", probability=True)
clf.fit(encodings, names)
dump(clf, 'clf.joblib')
return clf
def Face_Recognition_(self, frame):
small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
rgb_small_frame = small_frame[:, :, ::-1]
face_locations = face_recognition.face_locations(rgb_small_frame)
face_encodings = face_recognition.face_encodings(
rgb_small_frame, face_locations)
face_names = []
face_titles = []
for face_encoding in face_encodings:
matches = face_recognition.compare_faces(knownFE, face_encoding)
name = "Unknown"
title = "Unknown"
if True in matches:
first_match_index = matches.index(True)
name = knownN[first_match_index]
title = knownT[first_match_index]
face_names.append(name)
face_titles.append(title)
for (top, right, bottom,
left), name, title in zip(face_locations, face_names,
face_titles):
top *= 4
right *= 4
bottom *= 4
left *= 4
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
cv2.rectangle(frame, (left, bottom - 35), (right, bottom),
(0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, name + ": " + title, (left + 6, bottom - 6),
font, 1.0, (255, 255, 255), 1)
return frame, face_names, face_titles
# loop over the image paths
for (i, user) in enumerate(allUsers):
print("[INFO] processing user {}/{}".format(i + 1, len(allUsers)))
name = users.get_name_from_id(user)
for imagePath in users.get_pictures_from_id(user):
# load the input image and convert it from BGR (OpenCV ordering)
# to dlib ordering (RGB)
image = cv2.imread(imagePath)
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# detect the (x, y)-coordinates of the bounding boxes
# corresponding to each face in the input image
boxes = face_recognition.face_locations(rgb, \
model=args["detection_method"])
# compute the facial embedding for the face
encodings = face_recognition.face_encodings(rgb, boxes)
# loop over the encodings
for encoding in encodings:
# add each encoding + user(name) to our lists of known users and
# encodings
knownEncodings.append(encoding)
knownUsers.append(user)
# knownNames.append(name)
# dump the facial encodings + names to disk
print("[INFO] serializing encodings...")
data = {"encodings": knownEncodings, "users": knownUsers}