def create_model(db_path, model_name):
if model_name == 'VGG-Face':
print("Using VGG-Face model backend and")
model = VGGFace.loadModel()
input_shape = (224, 224)
elif model_name == 'OpenFace':
print("Using OpenFace model backend")
model = OpenFace.loadModel()
input_shape = (96, 96)
elif model_name == 'Facenet':
print("Using Facenet model backend")
model = Facenet.loadModel()
input_shape = (160, 160)
elif model_name == 'DeepFace':
print("Using FB DeepFace model backend")
model = FbDeepFace.loadModel()
input_shape = (152, 152)
elif model_name == 'DeepID':
print("Using DeepID model backend")
model = DeepID.loadModel()
input_shape = (55, 47)
elif model_name == 'Dlib':
print("Using Dlib model backend")
from deepface.basemodels.DlibResNet import DlibResNet
model = DlibResNet()
input_shape = (150, 150)
else:
raise ValueError("Invalid model_name passed - ", model_name)
return model, input_shape
def find(img_path,
db_path,
model_name='VGG-Face',
distance_metric='cosine',
model=None,
enforce_detection=True,
detector_backend='opencv'):
model_names = ['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace']
metric_names = ['cosine', 'euclidean', 'euclidean_l2']
tic = time.time()
if type(img_path) == list:
bulkProcess = True
img_paths = img_path.copy()
else:
bulkProcess = False
img_paths = [img_path]
if os.path.isdir(db_path) == True:
#---------------------------------------
if model == None:
if model_name == 'VGG-Face':
print("Using VGG-Face model backend and", distance_metric,
"distance.")
model = VGGFace.loadModel()
elif model_name == 'OpenFace':
print("Using OpenFace model backend", distance_metric,
"distance.")
model = OpenFace.loadModel()
elif model_name == 'Facenet':
print("Using Facenet model backend", distance_metric,
"distance.")
model = Facenet.loadModel()
elif model_name == 'DeepFace':
print("Using FB DeepFace model backend", distance_metric,
"distance.")
model = FbDeepFace.loadModel()
elif model_name == 'DeepID':
print("Using DeepID model backend", distance_metric,
"distance.")
model = DeepID.loadModel()
elif model_name == 'Dlib':
print("Using Dlib ResNet model backend", distance_metric,
"distance.")
model = DlibResNet()
elif model_name == 'Ensemble':
print("Ensemble learning enabled")
#TODO: include DeepID in ensemble method
import lightgbm as lgb #lightgbm==2.3.1
models = {}
pbar = tqdm(range(0, len(model_names)),
desc='Face recognition models')
for index in pbar:
if index == 0:
pbar.set_description("Loading VGG-Face")
models['VGG-Face'] = VGGFace.loadModel()
elif index == 1:
pbar.set_description("Loading FaceNet")
models['Facenet'] = Facenet.loadModel()
elif index == 2:
pbar.set_description("Loading OpenFace")
models['OpenFace'] = OpenFace.loadModel()
elif index == 3:
pbar.set_description("Loading DeepFace")
models['DeepFace'] = FbDeepFace.loadModel()
else:
raise ValueError("Invalid model_name passed - ", model_name)
else: #model != None
print("Already built model is passed")
if model_name == 'Ensemble':
import lightgbm as lgb #lightgbm==2.3.1
#validate model dictionary because it might be passed from input as pre-trained
found_models = []
for key, value in model.items():
found_models.append(key)
if ('VGG-Face'
in found_models) and ('Facenet' in found_models) and (
'OpenFace' in found_models) and ('DeepFace'
in found_models):
print("Ensemble learning will be applied for ",
found_models, " models")
else:
raise ValueError(
"You would like to apply ensemble learning and pass pre-built models but models must contain [VGG-Face, Facenet, OpenFace, DeepFace] but you passed "
+ found_models)
models = model.copy()
#threshold = functions.findThreshold(model_name, distance_metric)
#---------------------------------------
file_name = "representations_%s.pkl" % (model_name)
file_name = file_name.replace("-", "_").lower()
if path.exists(db_path + "/" + file_name):
print(
"WARNING: Representations for images in ", db_path,
" folder were previously stored in ", file_name,
". If you added new instances after this file creation, then please delete this file and call find function again. It will create it again."
)
f = open(db_path + '/' + file_name, 'rb')
representations = pickle.load(f)
print("There are ", len(representations),
" representations found in ", file_name)
else:
employees = []
for r, d, f in os.walk(
db_path): # r=root, d=directories, f = files
for file in f:
if ('.jpg' in file):
exact_path = r + "/" + file
employees.append(exact_path)
if len(employees) == 0:
raise ValueError("There is no image in ", db_path, " folder!")
#------------------------
#find representations for db images
representations = []
pbar = tqdm(range(0, len(employees)),
desc='Finding representations')
#for employee in employees:
for index in pbar:
employee = employees[index]
if model_name != 'Ensemble':
if model_name == 'Dlib': #non-keras model
input_shape = (150, 150, 3)
else:
#input_shape = model.layers[0].input_shape[1:3] #my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
input_shape = model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
#---------------------
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
img = functions.preprocess_face(
img=employee,
target_size=(input_shape_y, input_shape_x),
enforce_detection=enforce_detection,
detector_backend=detector_backend)
representation = model.predict(img)[0, :]
instance = []
instance.append(employee)
instance.append(representation)
else: #ensemble learning
instance = []
instance.append(employee)
for j in model_names:
ensemble_model = models[j]
#input_shape = model.layers[0].input_shape[1:3] #my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
input_shape = ensemble_model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
img = functions.preprocess_face(
img=employee,
target_size=(input_shape_y, input_shape_x),
enforce_detection=enforce_detection,
detector_backend=detector_backend)
representation = ensemble_model.predict(img)[0, :]
instance.append(representation)
#-------------------------------
representations.append(instance)
f = open(db_path + '/' + file_name, "wb")
pickle.dump(representations, f)
f.close()
print(
"Representations stored in ", db_path, "/", file_name,
" file. Please delete this file when you add new identities in your database."
)
#----------------------------
#we got representations for database
if model_name != 'Ensemble':
df = pd.DataFrame(representations,
columns=["identity", "representation"])
else: #ensemble learning
df = pd.DataFrame(representations,
columns=[
"identity", "VGG-Face_representation",
"Facenet_representation",
"OpenFace_representation",
"DeepFace_representation"
])
df_base = df.copy()
resp_obj = []
global_pbar = tqdm(range(0, len(img_paths)), desc='Analyzing')
for j in global_pbar:
img_path = img_paths[j]
#find representation for passed image
if model_name == 'Ensemble':
for j in model_names:
ensemble_model = models[j]
#input_shape = ensemble_model.layers[0].input_shape[1:3] #my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
input_shape = ensemble_model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
img = functions.preprocess_face(
img=img_path,
target_size=input_shape,
enforce_detection=enforce_detection,
detector_backend=detector_backend)
target_representation = ensemble_model.predict(img)[0, :]
for k in metric_names:
distances = []
for index, instance in df.iterrows():
source_representation = instance[
"%s_representation" % (j)]
if k == 'cosine':
distance = dst.findCosineDistance(
source_representation,
target_representation)
elif k == 'euclidean':
distance = dst.findEuclideanDistance(
source_representation,
target_representation)
elif k == 'euclidean_l2':
distance = dst.findEuclideanDistance(
dst.l2_normalize(source_representation),
dst.l2_normalize(target_representation))
distances.append(distance)
if j == 'OpenFace' and k == 'euclidean':
continue
else:
df["%s_%s" % (j, k)] = distances
#----------------------------------
feature_names = []
for j in model_names:
for k in metric_names:
if j == 'OpenFace' and k == 'euclidean':
continue
else:
feature = '%s_%s' % (j, k)
feature_names.append(feature)
#print(df[feature_names].head())
x = df[feature_names].values
#----------------------------------
#lightgbm model
home = str(Path.home())
if os.path.isfile(
home +
'/.deepface/weights/face-recognition-ensemble-model.txt'
) != True:
print(
"face-recognition-ensemble-model.txt will be downloaded..."
)
url = 'https://raw.githubusercontent.com/serengil/deepface/master/deepface/models/face-recognition-ensemble-model.txt'
output = home + '/.deepface/weights/face-recognition-ensemble-model.txt'
gdown.download(url, output, quiet=False)
ensemble_model_path = home + '/.deepface/weights/face-recognition-ensemble-model.txt'
deepface_ensemble = lgb.Booster(model_file=ensemble_model_path)
y = deepface_ensemble.predict(x)
verified_labels = []
scores = []
for i in y:
verified = np.argmax(i) == 1
score = i[np.argmax(i)]
verified_labels.append(verified)
scores.append(score)
df['verified'] = verified_labels
df['score'] = scores
df = df[df.verified == True]
#df = df[df.score > 0.99] #confidence score
df = df.sort_values(by=["score"],
ascending=False).reset_index(drop=True)
df = df[['identity', 'verified', 'score']]
resp_obj.append(df)
df = df_base.copy() #restore df for the next iteration
#----------------------------------
if model_name != 'Ensemble':
if model_name == 'Dlib': #non-keras model
input_shape = (150, 150, 3)
else:
#input_shape = model.layers[0].input_shape[1:3] #my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
input_shape = model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
#------------------------
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
img = functions.preprocess_face(
img=img_path,
target_size=(input_shape_y, input_shape_x),
enforce_detection=enforce_detection,
detector_backend=detector_backend)
target_representation = model.predict(img)[0, :]
distances = []
for index, instance in df.iterrows():
source_representation = instance["representation"]
if distance_metric == 'cosine':
distance = dst.findCosineDistance(
source_representation, target_representation)
elif distance_metric == 'euclidean':
distance = dst.findEuclideanDistance(
source_representation, target_representation)
elif distance_metric == 'euclidean_l2':
distance = dst.findEuclideanDistance(
dst.l2_normalize(source_representation),
dst.l2_normalize(target_representation))
else:
raise ValueError("Invalid distance_metric passed - ",
distance_metric)
distances.append(distance)
threshold = functions.findThreshold(model_name,
distance_metric)
df["distance"] = distances
df = df.drop(columns=["representation"])
df = df[df.distance <= threshold]
df = df.sort_values(by=["distance"],
ascending=True).reset_index(drop=True)
resp_obj.append(df)
df = df_base.copy() #restore df for the next iteration
toc = time.time()
print("find function lasts ", toc - tic, " seconds")
if len(resp_obj) == 1:
return resp_obj[0]
return resp_obj
else:
raise ValueError("Passed db_path does not exist!")
return None
def verify(img1_path,
img2_path='',
model_name='VGG-Face',
distance_metric='cosine',
model=None,
enforce_detection=True,
detector_backend='opencv'):
tic = time.time()
if type(img1_path) == list:
bulkProcess = True
img_list = img1_path.copy()
else:
bulkProcess = False
img_list = [[img1_path, img2_path]]
#------------------------------
resp_objects = []
if model_name == 'Ensemble':
print("Ensemble learning enabled")
import lightgbm as lgb #lightgbm==2.3.1
if model == None:
model = {}
model_pbar = tqdm(range(0, 4), desc='Face recognition models')
for index in model_pbar:
if index == 0:
model_pbar.set_description("Loading VGG-Face")
model["VGG-Face"] = VGGFace.loadModel()
elif index == 1:
model_pbar.set_description("Loading Google FaceNet")
model["Facenet"] = Facenet.loadModel()
elif index == 2:
model_pbar.set_description("Loading OpenFace")
model["OpenFace"] = OpenFace.loadModel()
elif index == 3:
model_pbar.set_description("Loading Facebook DeepFace")
model["DeepFace"] = FbDeepFace.loadModel()
#--------------------------
#validate model dictionary because it might be passed from input as pre-trained
found_models = []
for key, value in model.items():
found_models.append(key)
if ('VGG-Face' in found_models) and ('Facenet' in found_models) and (
'OpenFace' in found_models) and ('DeepFace' in found_models):
print("Ensemble learning will be applied for ", found_models,
" models")
else:
raise ValueError(
"You would like to apply ensemble learning and pass pre-built models but models must contain [VGG-Face, Facenet, OpenFace, DeepFace] but you passed "
+ found_models)
#--------------------------
model_names = ["VGG-Face", "Facenet", "OpenFace", "DeepFace"]
metrics = ["cosine", "euclidean", "euclidean_l2"]
pbar = tqdm(range(0, len(img_list)), desc='Verification')
#for instance in img_list:
for index in pbar:
instance = img_list[index]
if type(instance) == list and len(instance) >= 2:
img1_path = instance[0]
img2_path = instance[1]
ensemble_features = []
ensemble_features_string = "["
for i in model_names:
custom_model = model[i]
#input_shape = custom_model.layers[0].input_shape[1:3] #my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
input_shape = custom_model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
img1 = functions.preprocess_face(
img=img1_path,
target_size=input_shape,
enforce_detection=enforce_detection,
detector_backend=detector_backend)
img2 = functions.preprocess_face(
img=img2_path,
target_size=input_shape,
enforce_detection=enforce_detection,
detector_backend=detector_backend)
img1_representation = custom_model.predict(img1)[0, :]
img2_representation = custom_model.predict(img2)[0, :]
for j in metrics:
if j == 'cosine':
distance = dst.findCosineDistance(
img1_representation, img2_representation)
elif j == 'euclidean':
distance = dst.findEuclideanDistance(
img1_representation, img2_representation)
elif j == 'euclidean_l2':
distance = dst.findEuclideanDistance(
dst.l2_normalize(img1_representation),
dst.l2_normalize(img2_representation))
if i == 'OpenFace' and j == 'euclidean': #this returns same with OpenFace - euclidean_l2
continue
else:
ensemble_features.append(distance)
if len(ensemble_features) > 1:
ensemble_features_string += ", "
ensemble_features_string += str(distance)
#print("ensemble_features: ", ensemble_features)
ensemble_features_string += "]"
#-------------------------------
#find deepface path
home = str(Path.home())
if os.path.isfile(
home +
'/.deepface/weights/face-recognition-ensemble-model.txt'
) != True:
print(
"face-recognition-ensemble-model.txt will be downloaded..."
)
url = 'https://raw.githubusercontent.com/serengil/deepface/master/deepface/models/face-recognition-ensemble-model.txt'
output = home + '/.deepface/weights/face-recognition-ensemble-model.txt'
gdown.download(url, output, quiet=False)
ensemble_model_path = home + '/.deepface/weights/face-recognition-ensemble-model.txt'
#print(ensemble_model_path)
#-------------------------------
deepface_ensemble = lgb.Booster(model_file=ensemble_model_path)
prediction = deepface_ensemble.predict(
np.expand_dims(np.array(ensemble_features), axis=0))[0]
verified = np.argmax(prediction) == 1
if verified: identified = "true"
else: identified = "false"
score = prediction[np.argmax(prediction)]
#print("verified: ", verified,", score: ", score)
resp_obj = "{"
resp_obj += "\"verified\": " + identified
resp_obj += ", \"score\": " + str(score)
resp_obj += ", \"distance\": " + ensemble_features_string
resp_obj += ", \"model\": [\"VGG-Face\", \"Facenet\", \"OpenFace\", \"DeepFace\"]"
resp_obj += ", \"similarity_metric\": [\"cosine\", \"euclidean\", \"euclidean_l2\"]"
resp_obj += "}"
#print(resp_obj)
resp_obj = json.loads(resp_obj) #string to json
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
return resp_obj
#-------------------------------
if bulkProcess == True:
resp_obj = "{"
for i in range(0, len(resp_objects)):
resp_item = json.dumps(resp_objects[i])
if i > 0:
resp_obj += ", "
resp_obj += "\"pair_" + str(i + 1) + "\": " + resp_item
resp_obj += "}"
resp_obj = json.loads(resp_obj)
return resp_obj
return None
#ensemble learning block end
#--------------------------------
#ensemble learning disabled
if model == None:
if model_name == 'VGG-Face':
print("Using VGG-Face model backend and", distance_metric,
"distance.")
model = VGGFace.loadModel()
elif model_name == 'OpenFace':
print("Using OpenFace model backend", distance_metric, "distance.")
model = OpenFace.loadModel()
elif model_name == 'Facenet':
print("Using Facenet model backend", distance_metric, "distance.")
model = Facenet.loadModel()
elif model_name == 'DeepFace':
print("Using FB DeepFace model backend", distance_metric,
"distance.")
model = FbDeepFace.loadModel()
elif model_name == 'DeepID':
print("Using DeepID2 model backend", distance_metric, "distance.")
model = DeepID.loadModel()
elif model_name == 'Dlib':
print("Using Dlib ResNet model backend", distance_metric,
"distance.")
model = DlibResNet()
else:
raise ValueError("Invalid model_name passed - ", model_name)
else: #model != None
print("Already built model is passed")
#------------------------------
#face recognition models have different size of inputs
#my environment returns (None, 224, 224, 3) but some people mentioned that they got [(None, 224, 224, 3)]. I think this is because of version issue.
if model_name == 'Dlib': #this is not a regular keras model
input_shape = (150, 150, 3)
else: #keras based models
input_shape = model.layers[0].input_shape
if type(input_shape) == list:
input_shape = input_shape[0][1:3]
else:
input_shape = input_shape[1:3]
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
#------------------------------
#tuned thresholds for model and metric pair
threshold = functions.findThreshold(model_name, distance_metric)
#------------------------------
if len(img_list) > 1:
disable_option = False
else: #calling deepface in a for loop causes lots of progress bars. this block prevents this problem.
disable_option = True
pbar = tqdm(range(0, len(img_list)),
desc='Verification',
disable=disable_option)
#for instance in img_list:
for index in pbar:
instance = img_list[index]
if type(instance) == list and len(instance) >= 2:
img1_path = instance[0]
img2_path = instance[1]
#----------------------
#crop and align faces
img1 = functions.preprocess_face(
img=img1_path,
target_size=(input_shape_y, input_shape_x),
enforce_detection=enforce_detection,
detector_backend=detector_backend)
img2 = functions.preprocess_face(
img=img2_path,
target_size=(input_shape_y, input_shape_x),
enforce_detection=enforce_detection,
detector_backend=detector_backend)
#----------------------
#find embeddings
img1_representation = model.predict(img1)[0, :]
img2_representation = model.predict(img2)[0, :]
#----------------------
#find distances between embeddings
if distance_metric == 'cosine':
distance = dst.findCosineDistance(img1_representation,
img2_representation)
elif distance_metric == 'euclidean':
distance = dst.findEuclideanDistance(img1_representation,
img2_representation)
elif distance_metric == 'euclidean_l2':
distance = dst.findEuclideanDistance(
dst.l2_normalize(img1_representation),
dst.l2_normalize(img2_representation))
else:
raise ValueError("Invalid distance_metric passed - ",
distance_metric)
#----------------------
#decision
if distance <= threshold:
identified = "true"
else:
identified = "false"
#----------------------
#response object
resp_obj = "{"
resp_obj += "\"verified\": " + identified
resp_obj += ", \"distance\": " + str(distance)
resp_obj += ", \"max_threshold_to_verify\": " + str(threshold)
resp_obj += ", \"model\": \"" + model_name + "\""
resp_obj += ", \"similarity_metric\": \"" + distance_metric + "\""
resp_obj += "}"
resp_obj = json.loads(resp_obj) #string to json
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
#K.clear_session()
return resp_obj
#----------------------
else:
raise ValueError("Invalid arguments passed to verify function: ",
instance)
#-------------------------
toc = time.time()
#print("identification lasts ",toc-tic," seconds")
if bulkProcess == True:
resp_obj = "{"
for i in range(0, len(resp_objects)):
resp_item = json.dumps(resp_objects[i])
if i > 0:
resp_obj += ", "
resp_obj += "\"pair_" + str(i + 1) + "\": " + resp_item
resp_obj += "}"
resp_obj = json.loads(resp_obj)
return resp_obj
def loadModel():
return DlibResNet()
def DlibResNet_():
from deepface.basemodels.DlibResNet import DlibResNet
return DlibResNet()
def analysis(db_path, model_name, distance_metric, enable_face_analysis=True):
input_shape = (224, 224)
text_color = (255, 255, 255)
employees = []
#check passed db folder exists
if os.path.isdir(db_path) == True:
for r, d, f in os.walk(db_path): # r=root, d=directories, f = files
for file in f:
if ('.jpg' in file):
#exact_path = os.path.join(r, file)
exact_path = r + "/" + file
#print(exact_path)
employees.append(exact_path)
#------------------------
if len(employees) > 0:
if model_name == 'VGG-Face':
print("Using VGG-Face model backend and", distance_metric,
"distance.")
model = VGGFace.loadModel()
input_shape = (224, 224)
elif model_name == 'OpenFace':
print("Using OpenFace model backend", distance_metric, "distance.")
model = OpenFace.loadModel()
input_shape = (96, 96)
elif model_name == 'Facenet':
print("Using Facenet model backend", distance_metric, "distance.")
model = Facenet.loadModel()
input_shape = (160, 160)
elif model_name == 'DeepFace':
print("Using FB DeepFace model backend", distance_metric,
"distance.")
model = FbDeepFace.loadModel()
input_shape = (152, 152)
elif model_name == 'DeepID':
print("Using DeepID model backend", distance_metric, "distance.")
model = DeepID.loadModel()
input_shape = (55, 47)
elif model_name == 'Dlib':
print("Using Dlib model backend", distance_metric, "distance.")
model = DlibResNet()
input_shape = (150, 150)
else:
raise ValueError("Invalid model_name passed - ", model_name)
#------------------------
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
#tuned thresholds for model and metric pair
threshold = functions.findThreshold(model_name, distance_metric)
#------------------------
#facial attribute analysis models
if enable_face_analysis == True:
tic = time.time()
emotion_model = Emotion.loadModel()
print("Emotion model loaded")
age_model = Age.loadModel()
print("Age model loaded")
gender_model = Gender.loadModel()
print("Gender model loaded")
toc = time.time()
print("Facial attibute analysis models loaded in ", toc - tic,
" seconds")
#------------------------
#find embeddings for employee list
tic = time.time()
pbar = tqdm(range(0, len(employees)), desc='Finding embeddings')
embeddings = []
#for employee in employees:
for index in pbar:
employee = employees[index]
pbar.set_description("Finding embedding for %s" %
(employee.split("/")[-1]))
embedding = []
img = functions.detectFace(employee, (input_shape_y, input_shape_x))
img_representation = model.predict(img)[0, :]
embedding.append(employee)
embedding.append(img_representation)
embeddings.append(embedding)
df = pd.DataFrame(embeddings, columns=['employee', 'embedding'])
df['distance_metric'] = distance_metric
toc = time.time()
print("Embeddings found for given data set in ", toc - tic, " seconds")
#-----------------------
time_threshold = 5
frame_threshold = 5
pivot_img_size = 112 #face recognition result image
#-----------------------
opencv_path = functions.get_opencv_path()
face_detector_path = opencv_path + "haarcascade_frontalface_default.xml"
face_cascade = cv2.CascadeClassifier(face_detector_path)
#-----------------------
freeze = False
face_detected = False
face_included_frames = 0 #freeze screen if face detected sequantially 5 frames
freezed_frame = 0
tic = time.time()
cap = cv2.VideoCapture(0) #webcam
#cap = cv2.VideoCapture("C:/Users/IS96273/Desktop/skype-video-1.mp4") #video
while (True):
ret, img = cap.read()
#cv2.namedWindow('img', cv2.WINDOW_FREERATIO)
#cv2.setWindowProperty('img', cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN)
raw_img = img.copy()
resolution = img.shape
resolution_x = img.shape[1]
resolution_y = img.shape[0]
if freeze == False:
faces = face_cascade.detectMultiScale(img, 1.3, 5)
if len(faces) == 0:
face_included_frames = 0
else:
faces = []
detected_faces = []
face_index = 0
for (x, y, w, h) in faces:
if w > 130: #discard small detected faces
face_detected = True
if face_index == 0:
face_included_frames = face_included_frames + 1 #increase frame for a single face
cv2.rectangle(img, (x, y), (x + w, y + h), (67, 67, 67),
1) #draw rectangle to main image
cv2.putText(img, str(frame_threshold - face_included_frames),
(int(x + w / 4), int(y + h / 1.5)),
cv2.FONT_HERSHEY_SIMPLEX, 4, (255, 255, 255), 2)
detected_face = img[int(y):int(y + h),
int(x):int(x + w)] #crop detected face
#-------------------------------------
detected_faces.append((x, y, w, h))
face_index = face_index + 1
#-------------------------------------
if face_detected == True and face_included_frames == frame_threshold and freeze == False:
freeze = True
#base_img = img.copy()
base_img = raw_img.copy()
detected_faces_final = detected_faces.copy()
tic = time.time()
if freeze == True:
toc = time.time()
if (toc - tic) < time_threshold:
if freezed_frame == 0:
freeze_img = base_img.copy()
#freeze_img = np.zeros(resolution, np.uint8) #here, np.uint8 handles showing white area issue
for detected_face in detected_faces_final:
x = detected_face[0]
y = detected_face[1]
w = detected_face[2]
h = detected_face[3]
cv2.rectangle(freeze_img, (x, y), (x + w, y + h),
(67, 67, 67),
1) #draw rectangle to main image
#-------------------------------
#apply deep learning for custom_face
custom_face = base_img[y:y + h, x:x + w]
#-------------------------------
#facial attribute analysis
if enable_face_analysis == True:
gray_img = functions.detectFace(
custom_face, (48, 48), True)
emotion_labels = [
'Angry', 'Disgust', 'Fear', 'Happy', 'Sad',
'Surprise', 'Neutral'
]
emotion_predictions = emotion_model.predict(
gray_img)[0, :]
sum_of_predictions = emotion_predictions.sum()
mood_items = []
for i in range(0, len(emotion_labels)):
mood_item = []
emotion_label = emotion_labels[i]
emotion_prediction = 100 * emotion_predictions[
i] / sum_of_predictions
mood_item.append(emotion_label)
mood_item.append(emotion_prediction)
mood_items.append(mood_item)
emotion_df = pd.DataFrame(
mood_items, columns=["emotion", "score"])
emotion_df = emotion_df.sort_values(
by=["score"],
ascending=False).reset_index(drop=True)
#background of mood box
#transparency
overlay = freeze_img.copy()
opacity = 0.4
if x + w + pivot_img_size < resolution_x:
#right
cv2.rectangle(
freeze_img
#, (x+w,y+20)
,
(x + w, y),
(x + w + pivot_img_size, y + h),
(64, 64, 64),
cv2.FILLED)
cv2.addWeighted(overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
elif x - pivot_img_size > 0:
#left
cv2.rectangle(
freeze_img
#, (x-pivot_img_size,y+20)
,
(x - pivot_img_size, y),
(x, y + h),
(64, 64, 64),
cv2.FILLED)
cv2.addWeighted(overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
for index, instance in emotion_df.iterrows():
emotion_label = "%s " % (instance['emotion'])
emotion_score = instance['score'] / 100
bar_x = 35 #this is the size if an emotion is 100%
bar_x = int(bar_x * emotion_score)
if x + w + pivot_img_size < resolution_x:
text_location_y = y + 20 + (index + 1) * 20
text_location_x = x + w
if text_location_y < y + h:
cv2.putText(
freeze_img, emotion_label,
(text_location_x, text_location_y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 255, 255), 1)
cv2.rectangle(
freeze_img, (x + w + 70, y + 13 +
(index + 1) * 20),
(x + w + 70 + bar_x, y + 13 +
(index + 1) * 20 + 5),
(255, 255, 255), cv2.FILLED)
elif x - pivot_img_size > 0:
text_location_y = y + 20 + (index + 1) * 20
text_location_x = x - pivot_img_size
if text_location_y <= y + h:
cv2.putText(
freeze_img, emotion_label,
(text_location_x, text_location_y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 255, 255), 1)
cv2.rectangle(
freeze_img,
(x - pivot_img_size + 70, y + 13 +
(index + 1) * 20),
(x - pivot_img_size + 70 + bar_x,
y + 13 + (index + 1) * 20 + 5),
(255, 255, 255), cv2.FILLED)
#-------------------------------
face_224 = functions.detectFace(
custom_face, (224, 224), False)
age_predictions = age_model.predict(face_224)[0, :]
apparent_age = Age.findApparentAge(age_predictions)
#-------------------------------
gender_prediction = gender_model.predict(face_224)[
0, :]
if np.argmax(gender_prediction) == 0:
gender = "W"
elif np.argmax(gender_prediction) == 1:
gender = "M"
#print(str(int(apparent_age))," years old ", dominant_emotion, " ", gender)
analysis_report = str(
int(apparent_age)) + " " + gender
#-------------------------------
info_box_color = (46, 200, 255)
#top
if y - pivot_img_size + int(
pivot_img_size / 5) > 0:
triangle_coordinates = np.array([
(x + int(w / 2), y),
(x + int(w / 2) - int(w / 10),
y - int(pivot_img_size / 3)),
(x + int(w / 2) + int(w / 10),
y - int(pivot_img_size / 3))
])
cv2.drawContours(freeze_img,
[triangle_coordinates], 0,
info_box_color, -1)
cv2.rectangle(
freeze_img,
(x + int(w / 5), y - pivot_img_size +
int(pivot_img_size / 5)),
(x + w - int(w / 5),
y - int(pivot_img_size / 3)),
info_box_color, cv2.FILLED)
cv2.putText(freeze_img, analysis_report,
(x + int(w / 3.5),
y - int(pivot_img_size / 2.1)),
cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 111, 255), 2)
#bottom
elif y + h + pivot_img_size - int(
pivot_img_size / 5) < resolution_y:
triangle_coordinates = np.array([
(x + int(w / 2), y + h),
(x + int(w / 2) - int(w / 10),
y + h + int(pivot_img_size / 3)),
(x + int(w / 2) + int(w / 10),
y + h + int(pivot_img_size / 3))
])
cv2.drawContours(freeze_img,
[triangle_coordinates], 0,
info_box_color, -1)
cv2.rectangle(
freeze_img,
(x + int(w / 5),
y + h + int(pivot_img_size / 3)),
(x + w - int(w / 5), y + h +
pivot_img_size - int(pivot_img_size / 5)),
info_box_color, cv2.FILLED)
cv2.putText(freeze_img, analysis_report,
(x + int(w / 3.5), y + h +
int(pivot_img_size / 1.5)),
cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 111, 255), 2)
#-------------------------------
#face recognition
custom_face = functions.detectFace(
custom_face, (input_shape_y, input_shape_x))
#check detectFace function handled
if custom_face.shape[1:3] == input_shape:
if df.shape[
0] > 0: #if there are images to verify, apply face recognition
img1_representation = model.predict(
custom_face)[0, :]
#print(freezed_frame," - ",img1_representation[0:5])
def findDistance(row):
distance_metric = row['distance_metric']
img2_representation = row['embedding']
distance = 1000 #initialize very large value
if distance_metric == 'cosine':
distance = dst.findCosineDistance(
img1_representation,
img2_representation)
elif distance_metric == 'euclidean':
distance = dst.findEuclideanDistance(
img1_representation,
img2_representation)
elif distance_metric == 'euclidean_l2':
distance = dst.findEuclideanDistance(
dst.l2_normalize(
img1_representation),
dst.l2_normalize(
img2_representation))
return distance
df['distance'] = df.apply(findDistance, axis=1)
df = df.sort_values(by=["distance"])
candidate = df.iloc[0]
employee_name = candidate['employee']
best_distance = candidate['distance']
#print(candidate[['employee', 'distance']].values)
#if True:
if best_distance <= threshold:
#print(employee_name)
display_img = cv2.imread(employee_name)
display_img = cv2.resize(
display_img,
(pivot_img_size, pivot_img_size))
label = employee_name.split(
"/")[-1].replace(".jpg", "")
label = re.sub('[0-9]', '', label)
try:
if y - pivot_img_size > 0 and x + w + pivot_img_size < resolution_x:
#top right
freeze_img[
y - pivot_img_size:y,
x + w:x + w +
pivot_img_size] = display_img
overlay = freeze_img.copy()
opacity = 0.4
cv2.rectangle(
freeze_img, (x + w, y),
(x + w + pivot_img_size,
y + 20), (46, 200, 255),
cv2.FILLED)
cv2.addWeighted(
overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
cv2.putText(
freeze_img, label,
(x + w, y + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
text_color, 1)
#connect face and text
cv2.line(freeze_img,
(x + int(w / 2), y),
(x + 3 * int(w / 4), y -
int(pivot_img_size / 2)),
(67, 67, 67), 1)
cv2.line(freeze_img,
(x + 3 * int(w / 4), y -
int(pivot_img_size / 2)),
(x + w, y -
int(pivot_img_size / 2)),
(67, 67, 67), 1)
elif y + h + pivot_img_size < resolution_y and x - pivot_img_size > 0:
#bottom left
freeze_img[
y + h:y + h + pivot_img_size,
x -
pivot_img_size:x] = display_img
overlay = freeze_img.copy()
opacity = 0.4
cv2.rectangle(
freeze_img,
(x - pivot_img_size,
y + h - 20), (x, y + h),
(46, 200, 255), cv2.FILLED)
cv2.addWeighted(
overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
cv2.putText(
freeze_img, label,
(x - pivot_img_size,
y + h - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
text_color, 1)
#connect face and text
cv2.line(freeze_img,
(x + int(w / 2), y + h),
(x + int(w / 2) -
int(w / 4), y + h +
int(pivot_img_size / 2)),
(67, 67, 67), 1)
cv2.line(freeze_img,
(x + int(w / 2) -
int(w / 4), y + h +
int(pivot_img_size / 2)),
(x, y + h +
int(pivot_img_size / 2)),
(67, 67, 67), 1)
elif y - pivot_img_size > 0 and x - pivot_img_size > 0:
#top left
freeze_img[
y - pivot_img_size:y, x -
pivot_img_size:x] = display_img
overlay = freeze_img.copy()
opacity = 0.4
cv2.rectangle(
freeze_img,
(x - pivot_img_size, y),
(x, y + 20), (46, 200, 255),
cv2.FILLED)
cv2.addWeighted(
overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
cv2.putText(
freeze_img, label,
(x - pivot_img_size, y + 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
text_color, 1)
#connect face and text
cv2.line(
freeze_img,
(x + int(w / 2), y),
(x + int(w / 2) - int(w / 4),
y - int(pivot_img_size / 2)),
(67, 67, 67), 1)
cv2.line(
freeze_img,
(x + int(w / 2) - int(w / 4),
y - int(pivot_img_size / 2)),
(x,
y - int(pivot_img_size / 2)),
(67, 67, 67), 1)
elif x + w + pivot_img_size < resolution_x and y + h + pivot_img_size < resolution_y:
#bottom righ
freeze_img[
y + h:y + h + pivot_img_size,
x + w:x + w +
pivot_img_size] = display_img
overlay = freeze_img.copy()
opacity = 0.4
cv2.rectangle(
freeze_img,
(x + w, y + h - 20),
(x + w + pivot_img_size,
y + h), (46, 200, 255),
cv2.FILLED)
cv2.addWeighted(
overlay, opacity, freeze_img,
1 - opacity, 0, freeze_img)
cv2.putText(
freeze_img, label,
(x + w, y + h - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
text_color, 1)
#connect face and text
cv2.line(freeze_img,
(x + int(w / 2), y + h),
(x + int(w / 2) +
int(w / 4), y + h +
int(pivot_img_size / 2)),
(67, 67, 67), 1)
cv2.line(freeze_img,
(x + int(w / 2) +
int(w / 4), y + h +
int(pivot_img_size / 2)),
(x + w, y + h +
int(pivot_img_size / 2)),
(67, 67, 67), 1)
except Exception as err:
print(str(err))
tic = time.time(
) #in this way, freezed image can show 5 seconds
#-------------------------------
time_left = int(time_threshold - (toc - tic) + 1)
cv2.rectangle(freeze_img, (10, 10), (90, 50), (67, 67, 67),
-10)
cv2.putText(freeze_img, str(time_left), (40, 40),
cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 1)
cv2.imshow('img', freeze_img)
freezed_frame = freezed_frame + 1
else:
face_detected = False
face_included_frames = 0
freeze = False
freezed_frame = 0
else:
cv2.imshow('img', img)
if cv2.waitKey(1) & 0xFF == ord('q'): #press q to quit
break
#kill open cv things
cap.release()
cv2.destroyAllWindows()
vggface_model = VGGFace.loadModel()
elif index == 1:
pbar.set_description("Loading OpenFace")
openface_model = OpenFace.loadModel()
elif index == 2:
pbar.set_description("Loading Google FaceNet")
facenet_model = Facenet.loadModel()
elif index == 3:
pbar.set_description("Loading Facebook DeepFace")
deepface_model = FbDeepFace.loadModel()
elif index == 4:
pbar.set_description("Loading DeepID DeepFace")
deepid_model = DeepID.loadModel()
elif index == 5:
pbar.set_description("Loading Dlib ResNet DeepFace")
dlib_model = DlibResNet()
toc = time.time()
print("Face recognition models are built in ", toc - tic, " seconds")
#------------------------------
tic = time.time()
print("Loading Facial Attribute Analysis Models...")
pbar = tqdm(range(0, 4), desc='Loading Facial Attribute Analysis Models...')
for index in pbar:
if index == 0: