def scan_known_people(train_dir):
known_names = []
known_face_encodings = []
print("CNN image pre-process starting.........")
# Loop through each person in the training set
for class_dir in os.listdir(train_dir):
if not os.path.isdir(os.path.join(train_dir, class_dir)):
continue
# Loop through each training image for the current person
for file in image_files_in_folder(os.path.join(train_dir, class_dir)):
basename = os.path.splitext(os.path.basename(file))[0]
print('{} filename'.format(basename))
if (len(basename.split("_")) > 1):
member_firstname = basename.split('_')[0]
member_lastname = basename.split('_')[1]
else:
member_firstname = basename
member_lastname = ""
face_image = face_recognition.load_image_file(file)
face_locations = face_recognition.face_locations(
face_image, number_of_times_to_upsample=2, model='cnn')
encodings = face_recognition.face_encodings(
face_image,
known_face_locations=face_locations,
num_jitters=30)
if len(encodings) > 1:
click.echo(
"WARNING: More than one face found in {}. Only considering the first face."
.format(file))
if len(encodings) == 0:
click.echo(
"WARNING: No faces found in {}. Ignoring file.".format(
file))
else:
known_names.append(basename)
# known_face_encodings.append(encodings[0])
insertmember(member_firstname, member_lastname, encodings[0])
click.echo(f'Member {basename} has been added.', color='green')
def train(train_dir,
model_save_path=None,
n_neighbors=None,
knn_algo='auto',
verbose=True):
"""
Trains a k-nearest neighbors classifier for face recognition.
:param train_dir: directory that contains a sub-directory for each known person, with its name.
(View in source code to see train_dir example tree structure)
Structure:
<train_dir>/
├── <person1>/
│ ├── <somename1>.jpeg
│ ├── <somename2>.jpeg
│ ├── ...
├── <person2>/
│ ├── <somename1>.jpeg
│ └── <somename2>.jpeg
└── ...
:param model_save_path: (optional) path to save model on disk
:param n_neighbors: (optional) number of neighbors to weigh in classification. Chosen automatically if not specified
:param knn_algo: (optional) underlying data structure to support knn.default is ball_tree
:param verbose: verbosity of training
:return: returns knn classifier that was trained on the given data.
"""
X = []
y = []
# Loop through each person in the training set
for class_dir in os.listdir(train_dir):
if not os.path.isdir(os.path.join(train_dir, class_dir)):
continue
# Loop through each training image for the current person
for img_path in image_files_in_folder(
os.path.join(train_dir, class_dir)):
image = face_recognition.load_image_file(img_path)
face_bounding_boxes = face_recognition.face_locations(image)
if len(face_bounding_boxes) != 1:
# If there are no people (or too many people) in a training image, skip the image.
if verbose:
print("Image {} not suitable for training: {}".format(
img_path,
"Didn't find a face" if len(face_bounding_boxes) < 1
else "Found more than one face"))
else:
# Add face encoding for current image to the training set
X.append(
face_recognition.face_encodings(
image, known_face_locations=face_bounding_boxes)[0])
y.append(class_dir)
# Determine how many neighbors to use for weighting in the KNN classifier
if n_neighbors is None:
n_neighbors = int(round(math.sqrt(len(X))))
if verbose:
print("Chose n_neighbors automatically:", n_neighbors)
# Create and train the KNN classifier
knn_clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors,
algorithm=knn_algo,
weights='uniform')
knn_clf.fit(X, y)
# Save the trained KNN classifier
if model_save_path is not None:
with open(model_save_path, 'wb') as f:
pickle.dump(knn_clf, f)
return knn_clf
print("[INFO] quantifying faces...")
imagePaths = list(paths.list_images(args["dataset"]))
data = []
# loop over the image paths
for (i, imagePath) in enumerate(imagePaths):
# load the input image and convert it from RGB (OpenCV ordering)
# to dlib ordering (RGB)
print("[INFO] processing image {}/{}".format(i + 1, len(imagePaths)))
print(imagePath)
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)
# build a dictionary of the image path, bounding box location,
# and facial encodings for the current image
d = [{
"imagePath": imagePath,
"loc": box,
"encoding": enc
} for (box, enc) in zip(boxes, encodings)]
data.extend(d)
# dump the facial encodings data to disk
print("[INFO] serializing encodings...")
def imageparser():
#Initialize some variables
face_locations = []
face_encodings = []
#face_names = []
req = request
# convert string of image data to uint8
nparr = np.fromstring(req.data, np.uint8)
# decode image
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(
img, number_of_times_to_upsample=2)
face_encodings = face_recognition.face_encodings(img,
face_locations,
num_jitters=10)
face_names = []
# if the face is unknown look for the CNN model comparision
app.logger.info("Checking the CNN Model")
face_names, unidentified_face_encodings = mlearning.cnn_compare(
face_encodings)
# for x in face_new_names:
# face_names.append(x)
app.logger.info(
"Length of face_names : {}, unidentified names : {}".format(
len(face_names), len(unidentified_face_encodings)))
if (len(unidentified_face_encodings) >= 1):
#app.logger.info("face encodings {}".format(unidentified_face_encodings))
# # ------------------------------------------ KNN Model Prediction ------------------------------
# # Note: You can pass in either a classifier file name or a classifier model instance
predictions = mlearning.predict_without_location(
len(unidentified_face_encodings),
unidentified_face_encodings,
knn_clf=knn_clf,
model_path=None)
app.logger.info(predictions)
for name in predictions:
app.logger.debug("- Found {} ".format(name))
if (len(str(name).split("_")) > 1):
app.logger.debug("Name: " + str(name).split("_")[1])
face_names.append(str(name).split("_")[1])
else:
newfaceid = str(uuid.uuid4())
# using now() to get current time
current_time = datetime.datetime.now()
cv2.imwrite(
'./unidentified_images/' + newfaceid + '_' +
str(current_time) + '.jpg', img)
app.logger.debug('Found name - {}'.format(",".join(
str(x) for x in face_names)))
# # build a response dict to send back to client
response = {
'message': 'image received. size={}x{}'.format(img.shape[1],
img.shape[0]),
'details':
'Found name - {}'.format(",".join(str(x) for x in face_names))
}
# encode response using jsonpickle
response_pickled = jsonpickle.encode(response)
return Response(response=response_pickled,
status=200,
mimetype="application/json")