def vec_data(path):
mdl = fm.pose_predictor_model_location()
frm = fm.face_recognition_model_location()
cnn = dlib.face_recognition_model_v1(frm)
fd = dlib.get_frontal_face_detector()
im = cv.imread(path)
hi = (200, 200)
im = cv.resize(im, hi, interpolation=cv.INTER_AREA)
df = fd(im, 1)
a = []
if len(df) != 0:
fpose = dlib.shape_predictor(mdl)
pl = fpose(im, df[0])
vec = cnn.compute_face_descriptor(im, pl)
for z in range(len(vec)):
a.append(vec[z])
return a
else:
return a
def encode_filter(filter_files):
images = []
faces = []
FACE_ALIGNMENT = FaceAlignment(LandmarksType._2D,
enable_cuda=True,
flip_input=False)
for i, filter_file in enumerate(filter_files):
images.append(skimage.io.imread(str(filter_file)))
faces.append(FACE_ALIGNMENT.get_landmarks(images[i]))
FACE_ALIGNMENT = None
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
for i, face in enumerate(faces):
if face is None:
print('Warning: {} has no face.'.format(filter_files[i]))
continue
if len(face) > 1:
print('Warning: {} has more than one face.'.format(
filter_files[i]))
parts = []
for p in face[0]:
parts.append(dlib.point(p[0], p[1]))
raw_landmark_set = dlib.full_object_detection(rect, parts)
yield numpy.array(
face_encoder.compute_face_descriptor(images[i],
raw_landmark_set, 1))
def __init__(self,landmark_model="large"):
"""
Load previously encoded faces and their features
"""
with open('../../data/face_recognize_features.json') as f:
faces = json.load(f)
face_list = []
face_name_list = []
for face in faces:
for encoding in face['encodings']:
face_list.append(np.array(encoding))
face_name_list.append(face['name'])
self.face_list = np.array(face_list)
self.face_name_list = face_name_list
if landmark_model == "small":
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location()
self.pose_predictor = dlib.shape_predictor(predictor_5_point_model)
else:
predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
self.pose_predictor = dlib.shape_predictor(predictor_68_point_model)
face_recognition_model = face_recognition_models.face_recognition_model_location()
self.face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def __init__(self, filepath):
self.path = filepath
self.detector = dlib.get_frontal_face_detector()
self.win = dlib.image_window()
self.predictor_model = face_recognition_models.pose_predictor_model_location(
)
self.pose_predictor = dlib.shape_predictor(self.predictor_model)
self.face_recognition_model = face_recognition_models.face_recognition_model_location(
)
self.face_encoder = dlib.face_recognition_model_v1(
self.face_recognition_model)
def init_engine(mode='image', num_face=10, mask='all'):
if mask == 'recognize':
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location()
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
#predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
#pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
face_recognition_model = face_recognition_models.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
return pose_predictor_5_point, face_encoder
else:
face_detector = dlib.get_frontal_face_detector()
return face_detector
def __init__(self, gpu):
cuda.set_device(gpu)
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location(
)
pose_predictor_68_point = dlib.shape_predictor(
predictor_68_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
self.cnn_face_detector = dlib.cnn_face_detection_model_v1(
cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def __init__(self, ignore_gender=False):
self.file_log = open("log/file_log", "a")
self.img_size = 64
self.model = WideResNet(self.img_size, depth=16, k=8)()
self.model.load_weights(
os.path.join("pretrained_models", "weights.28-3.73.hdf5"))
self.image = None
self.detector = dlib.get_frontal_face_detector()
self.face_recognition_model = face_recognition_models.face_recognition_model_location(
)
self.face_encoder = dlib.face_recognition_model_v1(
self.face_recognition_model)
self.list_face = []
self.preload_list_face = True
self.logs = []
self.ignore_gender = ignore_gender
def __init__(self,
employees,
resolution=(320, 240),
model_type="small",
nb_iters=1):
# nb_iters - the higher is more percise but slower
# model_type - "small" / "large" large is more accurate but slower
self.camera = picamera.PiCamera()
self.camera.resolution = resolution
self.np_output = np.zeros((resolution[1], resolution[0], 3),
dtype=np.uint8)
self.model = frm.face_recognition_model_location()
self.encoder = dlib.face_recognition_model_v1(self.model)
self.face_detector = dlib.get_frontal_face_detector()
self.model_type = model_type
self.nb_iters = nb_iters
self.employees = employees
self.predictor = frm.pose_predictor_five_point_model_location()
if self.model_type == "large":
self.predictor = frm.face_recognition_models.pose_predictor_model_location(
)
self.load_faces()
import face_recognition_models
import time
import os
this_file_dir, _ = os.path.split(__file__)
landmarks_file_dir = os.path.join(this_file_dir,'shape_predictor_68_face_landmarks.dat')
# HOG face detector using the built-in dlib class
FACE_DETECTOR = dlib.get_frontal_face_detector()
# download the required pre-trained face detection model here:
# http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
PREDICTOR_MODEL = landmarks_file_dir
FACE_POSE_PREDICTOR = dlib.shape_predictor(PREDICTOR_MODEL)
FACE_RECOGNITION_MODEL = face_recognition_models.face_recognition_model_location()
FACE_ENCODER = dlib.face_recognition_model_v1(FACE_RECOGNITION_MODEL)
def _detect_faces(image, upsample_num_times):
"""
private function for detect faces using dlib
:param image:
:param upsample_num_times:
"""
# Run the HOG face detector on the image data.
return FACE_DETECTOR(image, upsample_num_times)
def detect_faces(image, upsample_num_times=1):
return _detect_faces(image, upsample_num_times)
video_path = "../video_clips/21_JUMP_STREET_DVS20.avi"
name_mappings = {"channing_tatum": "Jenko"}
actor_name = "channing_tatum"
actor_kb = []
print("video path: " + video_path)
print("name_mappings: \n\t{}".format(name_mappings))
print("actor_name: {} (single value for this test)".format(actor_name))
tatum_image_path = "./frame_1.png"
tatum_image = face_recognition.load_image_file(
tatum_image_path) #load image as numpy array in RGB format
predictor_path = face_recognition_models.models.shape_predictor_68_face_landmarks
face_rec_model_path = face_recognition_models.face_recognition_model_location()
# Load all the models we need: a detector to find the faces, a shape predictor
# to find face landmarks so we can precisely localize the face, and finally the
# face recognition model.
detector = dlib.get_frontal_face_detector() #HOG-Based
sp = dlib.shape_predictor(predictor_path)
facerec = dlib.face_recognition_model_v1(face_rec_model_path)
locations = detector(tatum_image)
landmarks = sp.__call__(tatum_image, locations[0])
# Using location of face, and shape predictor, generate the 128-Vector encoding of the face (the face descriptor)
encoding = facerec.compute_face_descriptor(tatum_image, )
def saveEncodings(self, verbose=True):
# initialize face encoding parameters
ImageFile.LOAD_TRUNCATED_IMAGES = True
predictor_68_point_model = face_recognition_models.pose_predictor_model_location(
)
pose_predictor_68_point = dlib.shape_predictor(
predictor_68_point_model)
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location(
)
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
pose_predictor = pose_predictor_68_point
# initialize a text file for saving images where faces are not found
with open('waste_files.txt', 'w') as waste:
waste.write("Images which are not suitable for training are-\n")
try:
# load previously saved encodings
pickle_in = open(self.base_dir + "known_face_encodings.pickle",
"rb")
known_face_encodings = pickle.load(pickle_in)
pickle_in.close()
pickle_in = open(self.base_dir + "known_face_names.pickle",
"rb")
known_face_names = pickle.load(pickle_in)
pickle_in.close()
# filter out faces which are already trained
temp = []
for name in self.names:
if name not in known_face_names:
temp.append(name)
self.names = temp
except:
# declare encodings as empty
known_face_encodings = []
known_face_names = []
#self.names = ['1231', '1232', '1234', '1238', '1242']#'1237', '1239','1235',
print("[INFO] Encoding... ", self.names)
if self.names != []:
# looping through names to be trained
for name in tqdm(self.names):
# clear the lists for new user
face_images = []
faces_locations = []
face_names = []
# load images of person to be trained
base = self.user_images
name = name.strip()
base = os.path.join(base, name)
# looping through images of person to be trained
for img_path in glob.glob(os.path.join(base, "*.jpg")):
# read image
image_data = cv2.imread(img_path)
###############
# check face using resnet
###############
blob = cv2.dnn.blobFromImage(image_data, 1.0,
(300, 300),
(104.0, 177.0, 123.0))
self.net2.setInput(blob)
detections = self.net2.forward()
(h, w) = image_data.shape[:2]
confidences = []
boxes = []
for i in range(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > 0.98:
box = detections[0, 0, i, 3:7] * np.array(
[w, h, w, h])
box = box.astype("int")
# startX, startY, endX, endY
confidences.append(float(confidence))
boxes.append([
box[0], box[1], box[2] - box[0],
box[3] - box[1]
])
if len(boxes) > 0:
pass
else:
waste.write(img_path + "\n")
#print("[INFO] Image {} not suitable for training: Resnet filtered out".format(img_path))
continue
###############
# face detection using yolo
###############
# load model parameters
blob = cv2.dnn.blobFromImage(image_data,
1 / 255, (416, 416),
[0, 0, 0],
1,
crop=False)
self.net.setInput(blob)
# fetch predictions from model/network
layers_names = self.net.getLayerNames()
outs = self.net.forward([
layers_names[i[0] - 1]
for i in self.net.getUnconnectedOutLayers()
])
# fetch size of image
(frame_height, frame_width) = image_data.shape[:2]
# declare overall confidence list
confidences = []
# declare bounding boxes list
boxes = []
face_locations = []
# looping through model predictions/ predictions for each grid cell
for out in outs:
# looping through detectors outputs for grid cell
for detection in out:
# fetch classifier probabilities for different classes
scores = detection[5:]
# fetch maximum probabilty class
class_id = np.argmax(scores)
# define confidence as maximum probability
confidence = scores[class_id]
# filter predictions based on confidence threshold
if confidence > self.yolo_conf_threshold:
# fetch bounding box dimensions
center_x = int(detection[0] * frame_width)
center_y = int(detection[1] * frame_height)
width = int(detection[2] * frame_width)
height = int(detection[3] * frame_height)
left = int(center_x - width / 2)
top = int(center_y - height / 2)
# append confidence in confidences list
confidences.append(float(confidence))
# append bounding box in bounding boxes list
boxes.append([left, top, width, height])
# perform non maximum suppression of overlapping images
indices = cv2.dnn.NMSBoxes(boxes, confidences,
self.yolo_conf_threshold,
self.nms_threshold)
# fetch faces bounding boxes
for i in indices:
i = i[0]
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
face_locations.append(
np.array([
top, left + width +
(width * self.margin // 100), top + height,
left - (width * self.margin // 100)
]))
if len(face_locations) != 1:
waste.write(img_path + "\n")
# If there are no people (or too many people) in a training image, skip the image.
if verbose:
pass
#print("[INFO] Image {} not suitable for training: {}".format(img_path, "Didn't find a face" if len(face_locations) < 1 else "Found more than one face"))
else:
for face_location in face_locations:
if min(face_location) < 0:
pass
#print("[INFO] Image {} not suitable for training: Face is not in Boundary of Image".format(img_path))
else:
######################################################
# histogram equalization
frame1 = image_data[
face_location[0]:face_location[2],
face_location[3]:face_location[1], :]
img_to_yuv = cv2.cvtColor(
frame1, cv2.COLOR_BGR2YUV)
img_to_yuv[:, :, 0] = cv2.equalizeHist(
img_to_yuv[:, :, 0])
frame1 = cv2.cvtColor(
img_to_yuv, cv2.COLOR_YUV2BGR)
image_data[
face_location[0]:face_location[2],
face_location[3]:
face_location[1], :] = frame1
###################################################
# Add face encoding for current image to the training set
faces_locations.append(face_locations[0])
face_images.append(image_data)
face_names.append(name)
faces_locations = [
self._css_to_rect(face_location)
for face_location in faces_locations
]
raw_landmarks = []
for face_image, face_location in zip(
face_images, faces_locations):
faces = dlib.full_object_detections()
faces.append(pose_predictor(face_image, face_location))
raw_landmarks.append(faces)
if len(faces_locations) < 120:
print(
"[INFO]: %s skipped as total number of proper images are <120."
% name)
continue
# generate encoding for captured faces of user
encodings = list(np.array(face_encoder.compute_face_descriptor(batch_img=face_images, batch_faces=raw_landmarks, num_jitters=20))\
.reshape((len(face_images), 128)))
# append new data in old data
known_face_encodings += encodings
known_face_names += face_names
# save the encodings after every iteration of distinct class
pickle_out = open(
self.base_dir + "known_face_names.pickle", "wb")
pickle.dump(known_face_names, pickle_out)
pickle_out.close()
pickle_out = open(
self.base_dir + "known_face_encodings.pickle", "wb")
pickle.dump(known_face_encodings, pickle_out)
pickle_out.close()
print("[INFO]: %s saved!" % name)
else:
print("Encoding Skipped!\n")
def run(video_path, actor_kb, stride=3):
# setup the face detector & encoder for use on each frame
detector = dlib.get_frontal_face_detector()
shape_predictor_path = face_recognition_models.pose_predictor_model_location(
)
sp = dlib.shape_predictor(shape_predictor_path)
facerec_model_path = face_recognition_models.face_recognition_model_location(
)
recognizer = dlib.face_recognition_model_v1(facerec_model_path)
# Add face reference encodings to our version of KB
# TODO: untested
detector = dlib.get_frontal_face_detector()
sp_path = face_recognition_models.pose_predictor_model_location()
sp = dlib.shape_predictor(sp_path)
rec_path = face_recognition_models.face_recognition_model_location()
rec = dlib.face_recognition_model_v1(rec_path)
for actor_name, actor_info in actor_kb.items():
image = cv2.imread(actor_info["image_path"])
face_rgb = image[:, :, ::-1]
locations = detector(face_rgb)
# Assume there's only one face in the reference image
detection_object = sp(face_rgb, locations[0])
encoding = rec.compute_face_descriptor(face_rgb, detection_object,
REC_JITTER)
actor_kb[actor_name]["encoding"] = encoding
# split record list into lists of the columns (keeping order) for input into recognizer functions
# maintaining order between the lists for easy referencing later on
# eg: known_encodings[1] is from the same record as known_characters[1], etc
known_encodings = []
known_characters = []
counts = []
for actor_name, record in actor_kb.items():
known_encodings.append(record['encoding'])
known_characters.append(record['character'])
counts.append(0)
# Open the input movie file
input_movie = cv2.VideoCapture(video_path)
length = int(input_movie.get(cv2.CAP_PROP_FRAME_COUNT))
FPS = input_movie.get(cv2.CAP_PROP_FPS)
width = int(input_movie.get(cv2.CAP_PROP_FRAME_WIDTH)) #1280
height = int(input_movie.get(cv2.CAP_PROP_FRAME_HEIGHT)) #720
# Initialize some variables
face_locations = []
detected_faces_encodings = []
recognized_faces_names = []
frame_number = 0
for actor_name, actor_info in actor_kb.items():
actor_kb[actor_name]["count"] = 0
frames_analysed = 0
print("\n\trecognizer: Finished Setup, entering loop!\n\tINPUT VIDEO: {}".
format(video_path))
while True:
# READ FRAME IN
# Grab a single frame of video
ret, frame = input_movie.read()
# Quit when the input video file ends
if not ret:
break
frame_number += 1
if not frame_number % stride == 0:
continue
frames_analysed += 1
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_frame = frame[:, :, ::-1]
frame_copy = frame.copy()
# BEGIN FACE DETECTION & ENCODING OVER THE FRAME. (find ALL faces in the frame. NB: Encoding is like analysing a face. Recognition is encoding + comparing to some kb of encodings)
locations = detector(rgb_frame)
full_object_detections = []
for location in locations:
full_object_detections.append(
sp(rgb_frame, location)
) # An array of type full_object_detection[]. This object contains fields like the landmark points, but we pass the full thing to the recognizer
detected_faces_encodings = []
# For each detected face, compute the face descriptor
# Jitter can improve quality of encoding, but increases the time taken in direct proportion to the number of jitters (jitter of 100 -> 100x as long)
if REC_JITTER == 0:
for landmarks in full_object_detections:
detected_faces_encodings.append(
recognizer.compute_face_descriptor(rgb_frame, landmarks))
else:
for landmarks in full_object_detections:
detected_faces_encodings.append(
recognizer.compute_face_descriptor(rgb_frame, landmarks,
REC_JITTER))
# print("Done. Got encodings for {} faces, from {} object detections".format(len(detected_faces_encodings),len(full_object_detections)))
# print("\nStarting to compare the encodings in knowledge base to those found in the image")
# COMPARE FACES FOUND IN IMAGE TO KNOWN FACES, THEN SAVE NAMES OF THOSE RECOGNIZED
recognized_faces_names = []
encodings_match = []
for count, face_encoding in enumerate(detected_faces_encodings):
# calculate Euclidian distance (similarity) between this face encoding and each known face encodings.
encodings_match = [
np.linalg.norm(
np.array(known_encodings[i]) - np.array(face_encoding)) <=
COMPARISON_TOLERANCE for i in range(0, len(known_encodings))
]
# finally, match any recognized encoding to the associated name.
name = None
for i in range(0, len(encodings_match)):
if encodings_match[i]:
name = known_characters[i]
counts[i] += 1
break
recognized_faces_names.append(name)
print("\n***Recognized: {}".format(recognized_faces_names))
#print("\nDone Comparing")
#print("\tCurrent count: ")
#for i, character_name in enumerate(known_characters):
# print("\t{} : {}".format(character_name , counts[i]))
# FINISHED RECOGNIZING
if __name__ == "__main__":
write_sample_frames(locations, frame_copy, full_object_detections,
frame_number)
#print("{}, {}".format(frame_number/FPS, recognized_faces_names))
#print("\n\tRecognizer: Finished processing {}".format(video_path))
input_movie.release()
cv2.destroyAllWindows()
# Store counts for each actor in an updated knowledge base
characters_to_actors = {}
for actor_name, info in actor_kb.items():
characters_to_actors[info["character"]] = actor_name
for i, name in enumerate(known_characters):
actor_kb[characters_to_actors[name]]["count"] = counts[i]
del actor_kb[characters_to_actors[name]]["encoding"]
print(
"\tRecognizer: getPercentages:run:\n\t\ttotal_frames == {}\n\t\tStride == {}\n\t\tReturning tuple: (actor_kb, frames_analysed) == ({},{})"
.format(frame_number, STRIDE, actor_kb, frames_analysed))
input("Continue?")
return (actor_kb, frames_analysed, frame_number)
class FaceRecognizer:
ImageFile.LOAD_TRUNCATED_IMAGES = True
predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
face_recognition_model = face_recognition_models.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
detector = MTCNN()
def __init__ (self):
self.clf = None
return
def img_load(self,img_dir):
img = imageio.imread(img_dir)
img = np.asarray(img)
return img
def _raw_face_landmarks(self, face_image, face_locations=None, model="large"):
pose_predictor = self.pose_predictor_68_point
return [pose_predictor(face_image, face_location) for face_location in face_locations]
def face_encodings(self, face_image, known_face_locations=None, num_jitters=2):
"""
Given an image, return the 128-dimension face encoding for each face in the image.
:param face_image: The image that contains one or more faces
:param known_face_locations: Optional - the bounding boxes of each face if you already know them.
:param num_jitters: How many times to re-sample the face when calculating encoding. Higher is more accurate, but slower (i.e. 100 is 100x slower)
:return: A list of 128-dimensional face encodings (one for each face in the image)
"""
raw_landmarks = self._raw_face_landmarks(face_image, known_face_locations)
return [np.array(self.face_encoder.compute_face_descriptor(face_image, raw_landmark_set, num_jitters)) for raw_landmark_set in raw_landmarks]
def predict_and_encode (self, img, confidence = 0.9,ratio = 30,visua = False):
predict = self.detector.detect_faces(img)
#print(predict)
out_boxes = [ item['box'] for item in predict if item["confidence"]> confidence and item["box"][3]>img.shape[0]/ratio]
out_boxes = dlib.rectangles([dlib.rectangle(a,b,a+c,b+d) for a,b,c,d in out_boxes ])
#print(out_boxes)
key = [item['keypoints'] for item in predict if item["confidence"]> confidence and item["box"][3]>img.shape[0]/ratio]
img_encoded = self.face_encodings(img,out_boxes)
#print(key)
if visua:
self.visualize(img,out_boxes,key)
return out_boxes, key, img_encoded
def visualize(self, img,out_boxes,key,name = []):
img2 = img.copy()
plt.figure(figsize=(15, 15))
for i, c in list(enumerate(out_boxes)):
box = out_boxes[i]
cv2.rectangle(img2,(box.left(),box.top()),(box.right(),box.bottom()),(0,255,0),int(img.shape[1]/150))
if len(name) != 0:
plt.text(box.left(),box.top(),name[i],fontsize = img.shape[0]/50, color = 'red')
keyx = [item[0] for item in key[i].values()]
keyy = [item[1] for item in key[i].values()]
#print(keyx,keyy)
#plt.plot(keyx,keyy,'bo')
plt.axis('off')
plt.imshow(img2)
#plt.savefig("/content/drive/My Drive/predict.png", bbox_inches='tight', pad_inches=0)
plt.show()
def init_KNN(self, X_train, y_train):
clf = neighbors.KNeighborsClassifier(n_neighbors = 15, p = 2, weights = 'distance', n_jobs = -1)
clf.fit(X_train, y_train)
self.clf = clf
def search_face(self, img):
out_boxes, key, img_encoded = self.predict_and_encode (img)
print(len(img_encoded))
if len(img_encoded)==0:
print("can not search")
else:
results = self.clf.predict(img_encoded)
score = self.clf.predict_proba(img_encoded)
print(results)
#print(score)
final_results = []
for i in range (len(results)):
if max(score[i])>0.8:
final_results.append(results[i])
else:
final_results.append("unknown")
print(final_results)
self.visualize(img,out_boxes,key,final_results)
def filter_face(input_dir, output_dir, processn, alignments, fps,
filter_encodings, workerqueue):
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
filter_threshold = 0.56
def encode_one_face_local(image, faces):
for points in faces:
parts = []
for p in points:
parts.append(dlib.point(p[0], p[1]))
raw_landmark_set = dlib.full_object_detection(rect, parts)
yield numpy.array(
face_encoder.compute_face_descriptor(image, raw_landmark_set,
1))
container = av.open(input_dir)
stream = container.streams.video[0]
container.seek(int(alignments[0][0] * stream.time_base * 1000000))
fps = 1 / fps
idx = 0
length = len(alignments)
frame = next(f for f in container.decode(video=0))
timenext = frame.pts * stream.time_base + fps
def process_frame():
nonlocal idx
while (idx < length) and (alignments[idx][0] < frame.pts):
idx += 1
face_files = []
faces = []
while (idx < length) and (frame.pts == alignments[idx][0]):
face_file = output_dir / alignments[idx][1]
if face_file.exists():
face_files.append(face_file)
faces.append(
numpy.array(alignments[idx][3]).reshape(
(-1, 2)).astype(int))
idx += 1
if len(face_files) > 0:
scores = []
encodings = list(
encode_one_face_local(frame.to_nd_array(format='rgb24'),
faces))
min = 1
for (face_file, encoding) in zip(face_files, encodings):
score = numpy.linalg.norm(filter_encodings - encoding, axis=1)
scores.append(score)
t = score.min()
if t < min:
min = t
if t > filter_threshold:
face_file.replace(output_dir / 'filter1' / face_file.name)
if len(face_files) > 1:
for i, face_file in enumerate(face_files):
if face_file.exists() and scores[i].min() > min:
face_file.replace(output_dir / 'filter2' /
face_file.name)
workerqueue.put((processn, idx, face_files, scores))
process_frame()
for frame in container.decode(video=0):
timenow = frame.pts * stream.time_base
if (timenow >= timenext):
timenext += fps
process_frame()
if idx >= length:
break
workerqueue.put(None)
import dlib
import skimage as sk
import numpy as np
import cv2 as cv
import csv
import simplejson as sj
import face_recognition
import simplejson as sj
import socket
import random
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.connect(('127.0.0.1', 5000))
mdl = fm.pose_predictor_model_location()
frm = fm.face_recognition_model_location()
cnn = dlib.face_recognition_model_v1(frm)
fd = dlib.get_frontal_face_detector()
im = cv.imread('test.jpg')
hi = (200, 200)
im = cv.resize(im, hi, interpolation=cv.INTER_AREA)
df = fd(im, 1)
if len(df) != 0:
fpose = dlib.shape_predictor(mdl)
pl = fpose(im, df[0])
print()
print("pip install git+https://github.com/ageitgey/face_recognition_models")
quit()
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location()
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location()
cnn_face_detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def _rect_to_css(rect):
"""
Convert a dlib 'rect' object to a plain tuple in (top, right, bottom, left) order
:param rect: a dlib 'rect' object
:return: a plain tuple representation of the rect in (top, right, bottom, left) order
"""
return rect.top(), rect.right(), rect.bottom(), rect.left()
def _css_to_rect(css):
"""
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location(
)
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location(
)
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
cnn_face_detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def _rect_to_css(rect):
"""
Convert a dlib 'rect' object to a plain tuple in (top, right, bottom, left) order
:param rect: a dlib 'rect' object
:return: a plain tuple representation of the rect in (top, right, bottom, left) order
"""
return rect.top(), rect.right(), rect.bottom(), rect.left()
def _css_to_rect(css):
"""
def main(mode='test', img_path='def'):
t = time.clock()
classes = [
'MXG', 'Sanaken', 'Zofinka', 'Toalk', 'Zissxzirsziiss', 'kiasummer'
]
known_face_encodes = [
np.loadtxt(MAIN_PATH + '/persons/MXG/fv.txt'),
np.loadtxt(MAIN_PATH + '/persons/Sanaken/fv.txt'),
np.loadtxt(MAIN_PATH + '/persons/Zofinka/fv.txt'),
np.loadtxt(MAIN_PATH + '/persons/Toalk/fv.txt'),
np.loadtxt(MAIN_PATH + '/persons/Zissxzirsziiss/fv.txt'),
np.loadtxt(MAIN_PATH + '/persons/kiasummer/fv.txt')
]
known_face_encodes = np.reshape(known_face_encodes, (6, 5, 128))
# get image
if img_path == 'def':
image = cv2.imread('team.jpg', 1)
else:
image = cv2.imread(img_path, 1)
# output
init_align_faces = []
out_arr = []
# get bboxes
fd = FaceDetector()
conf, faceboxes, mboxes = fd.get_faceboxes(image)
color = [255, 255, 255]
# border widths; I set them all to 150
top, bottom, left, right = [120] * 4
image = cv2.copyMakeBorder(image,
top,
bottom,
left,
right,
cv2.BORDER_CONSTANT,
value=color)
bbox_mark_image = image.copy()
# get alignment model
predictor_model = MAIN_PATH + "/models/shape_predictor_68_face_landmarks.dat"
face_pose_predictor = dlib.shape_predictor(predictor_model)
face_aligner = openface.AlignDlib(predictor_model)
# init predection model
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location(
)
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
for i in range(len(faceboxes)):
# get dlib rectangle from facebox
face_rect = dlib.rectangle(faceboxes[i][0], faceboxes[i][1],
faceboxes[i][2], faceboxes[i][3])
# Get the the face's pose
pose_landmarks = face_pose_predictor(image, face_rect)
# Use openface to calculate and perform the face alignment
alignedFace = face_aligner.align(
534,
image,
face_rect,
landmarkIndices=openface.AlignDlib.OUTER_EYES_AND_NOSE)
alignedFace_out = cv2.resize(alignedFace,
(faceboxes[i][2] - faceboxes[i][0],
faceboxes[i][3] - faceboxes[i][1]))
initFace_out = image[faceboxes[i][1]:faceboxes[i][3],
faceboxes[i][0]:faceboxes[i][2]]
init_align_faces.append([initFace_out, alignedFace_out])
# draw marks
parts = dlib.full_object_detection.parts(pose_landmarks)
FaceDetector.draw_marks(bbox_mark_image, parts)
# get face landmarks for feature extraction
landmark_set = pose_predictor_5_point(
alignedFace,
dlib.rectangle(0, 0, alignedFace.shape[0], alignedFace.shape[1]))
# get feature vector
feature_vector = np.array(
face_encoder.compute_face_descriptor(alignedFace, landmark_set, 1))
# known_face_encode = np.loadtxt('persons/MXG/fv.txt')
ind = compare_faces(known_face_encodes, feature_vector)
if (ind != -1):
face_class = classes[ind]
colour = (0, 255, 0)
else:
face_class = "Unknown"
colour = (0, 0, 255)
sh = max(image.shape[0], image.shape[1])
mult = sh / 500
if mult < 1:
mult = 1
cv2.putText(image, face_class, (faceboxes[i][0], faceboxes[i][1] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5 * mult, colour, 1)
cv2.rectangle(bbox_mark_image, (faceboxes[i][0], faceboxes[i][1]),
(faceboxes[i][2], faceboxes[i][3]), (0, 255, 0))
cv2.rectangle(image, (faceboxes[i][0], faceboxes[i][1]),
(faceboxes[i][2], faceboxes[i][3]), (0, 255, 0))
#cv2.rectangle(image, (mboxes[i][0], mboxes[i][1]), (mboxes[i][2], mboxes[i][3]), (0, 255, 0))
#out_arr.append({'x1': faceboxes[i][0], 'y1': faceboxes[i][1], 'x2': faceboxes[i][2], 'y2': faceboxes[i][3], 'class': face_class, 'conf': conf[i]})
out_arr.append({
'x1': mboxes[i][0],
'y1': mboxes[i][1],
'x2': mboxes[i][2],
'y2': mboxes[i][3],
'class': face_class,
'conf': conf[i]
})
t = time.clock() - t
out_imgs = [image, bbox_mark_image, init_align_faces, t]
if mode == 'test':
cv2.imshow("Preview", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
if mode == 'metr':
#cv2.imshow("Preview", image)
#cv2.waitKey(0)
#cv2.destroyAllWindows()
return out_arr
if mode == 'process':
return out_imgs
if mode == 'def':
return out_imgs