def analysis(db_path,
model_name,
distance_metric,
enable_face_analysis=True,
source=0,
time_threshold=5,
frame_threshold=5):
input_shape = (224, 224)
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
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:
print("WARNING: There is no image in this path ( ", db_path,
") . Face recognition will not be performed.")
#------------------------
if len(employees) > 0:
model = DeepFace.build_model(model_name)
print(model_name, " is built")
#------------------------
input_shape = functions.find_input_shape(model)
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
#tuned thresholds for model and metric pair
threshold = dst.findThreshold(model_name, distance_metric)
#------------------------
#facial attribute analysis models
if enable_face_analysis == True:
tic = time.time()
emotion_model = DeepFace.build_model('Emotion')
print("Emotion model loaded")
age_model = DeepFace.build_model('Age')
print("Age model loaded")
gender_model = DeepFace.build_model('Gender')
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.preprocess_face(img=employee,
target_size=(input_shape_y,
input_shape_x),
enforce_detection=False)
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")
#-----------------------
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(source) #webcam
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.preprocess_face(
img=custom_face,
target_size=(48, 48),
grayscale=True,
enforce_detection=False)
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.preprocess_face(
img=custom_face,
target_size=(224, 224),
grayscale=False,
enforce_detection=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.preprocess_face(
img=custom_face,
target_size=(input_shape_y, input_shape_x),
enforce_detection=False)
#check preprocess_face 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()
def verify(img1_path,
img2_path='',
model_name='VGG-Face',
distance_metric='cosine',
model=None,
enforce_detection=True,
detector_backend='mtcnn'):
"""
This function verifies an image pair is same person or different persons.
Parameters:
img1_path, img2_path: exact image path, numpy array or based64 encoded images could be passed. If you are going to call verify function for a list of image pairs, then you should pass an array instead of calling the function in for loops.
e.g. img1_path = [
['img1.jpg', 'img2.jpg'],
['img2.jpg', 'img3.jpg']
]
model_name (string): VGG-Face, Facenet, OpenFace, DeepFace, DeepID, Dlib, ArcFace or Ensemble
distance_metric (string): cosine, euclidean, euclidean_l2
model: Built deepface model. A face recognition model is built every call of verify function. You can pass pre-built face recognition model optionally if you will call verify function several times.
model = DeepFace.build_model('VGG-Face')
enforce_detection (boolean): If any face could not be detected in an image, then verify function will return exception. Set this to False not to have this exception. This might be convenient for low resolution images.
detector_backend (string): set face detector backend as mtcnn, opencv, ssd or dlib
Returns:
Verify function returns a dictionary. If img1_path is a list of image pairs, then the function will return list of dictionary.
{
"verified": True
, "distance": 0.2563
, "max_threshold_to_verify": 0.40
, "model": "VGG-Face"
, "similarity_metric": "cosine"
}
"""
tic = time.time()
img_list, bulkProcess = functions.initialize_input(img1_path, img2_path)
functions.initialize_detector(detector_backend=detector_backend)
resp_objects = []
#--------------------------------
if model_name == 'Ensemble':
model_names = ["VGG-Face", "Facenet", "OpenFace", "DeepFace"]
metrics = ["cosine", "euclidean", "euclidean_l2"]
else:
model_names = []
metrics = []
model_names.append(model_name)
metrics.append(distance_metric)
#--------------------------------
if model == None:
if model_name == 'Ensemble':
models = Boosting.loadModel()
else:
model = build_model(model_name)
models = {}
models[model_name] = model
else:
if model_name == 'Ensemble':
Boosting.validate_model(model)
models = model.copy()
else:
models = {}
models[model_name] = model
#------------------------------
#calling deepface in a for loop causes lots of progress bars. this prevents it.
disable_option = False if len(img_list) > 1 else True
pbar = tqdm(range(0, len(img_list)),
desc='Verification',
disable=disable_option)
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 = []
for i in model_names:
custom_model = models[i]
#decide input shape
input_shape = functions.find_input_shape(custom_model)
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
#----------------------
#detect 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 = custom_model.predict(img1)[0, :]
img2_representation = custom_model.predict(img2)[0, :]
#----------------------
#find distances between embeddings
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))
else:
raise ValueError("Invalid distance_metric passed - ",
distance_metric)
distance = np.float64(
distance
) #causes trobule for euclideans in api calls if this is not set (issue #175)
#----------------------
#decision
if model_name != 'Ensemble':
threshold = dst.findThreshold(i, j)
if distance <= threshold:
identified = True
else:
identified = False
resp_obj = {
"verified": identified,
"distance": distance,
"max_threshold_to_verify": threshold,
"model": model_name,
"similarity_metric": distance_metric
}
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
return resp_obj
else: #Ensemble
#this returns same with OpenFace - euclidean_l2
if i == 'OpenFace' and j == 'euclidean':
continue
else:
ensemble_features.append(distance)
#----------------------
if model_name == 'Ensemble':
boosted_tree = Boosting.build_gbm()
prediction = boosted_tree.predict(
np.expand_dims(np.array(ensemble_features), axis=0))[0]
verified = np.argmax(prediction) == 1
score = prediction[np.argmax(prediction)]
resp_obj = {
"verified": verified,
"score": score,
"distance": ensemble_features,
"model": ["VGG-Face", "Facenet", "OpenFace", "DeepFace"],
"similarity_metric":
["cosine", "euclidean", "euclidean_l2"]
}
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
return resp_obj
#----------------------
else:
raise ValueError("Invalid arguments passed to verify function: ",
instance)
#-------------------------
toc = time.time()
if bulkProcess == True:
resp_obj = {}
for i in range(0, len(resp_objects)):
resp_item = resp_objects[i]
resp_obj["pair_%d" % (i + 1)] = resp_item
return resp_obj
def find(img_path,
db_path,
model_name='VGG-Face',
distance_metric='cosine',
model=None,
enforce_detection=True,
detector_backend='mtcnn'):
"""
This function applies verification several times and find an identity in a database
Parameters:
img_path: exact image path, numpy array or based64 encoded image. If you are going to find several identities, then you should pass img_path as array instead of calling find function in a for loop. e.g. img_path = ["img1.jpg", "img2.jpg"]
db_path (string): You should store some .jpg files in a folder and pass the exact folder path to this.
model_name (string): VGG-Face, Facenet, OpenFace, DeepFace, DeepID, Dlib or Ensemble
distance_metric (string): cosine, euclidean, euclidean_l2
model: built deepface model. A face recognition models are built in every call of find function. You can pass pre-built models to speed the function up.
model = DeepFace.build_model('VGG-Face')
enforce_detection (boolean): The function throws exception if a face could not be detected. Set this to True if you don't want to get exception. This might be convenient for low resolution images.
detector_backend (string): set face detector backend as mtcnn, opencv, ssd or dlib
Returns:
This function returns pandas data frame. If a list of images is passed to img_path, then it will return list of pandas data frame.
"""
tic = time.time()
img_paths, bulkProcess = functions.initialize_input(img_path)
functions.initialize_detector(detector_backend=detector_backend)
#-------------------------------
if os.path.isdir(db_path) == True:
if model == None:
if model_name == 'Ensemble':
print("Ensemble learning enabled")
models = Boosting.loadModel()
else: #model is not ensemble
model = build_model(model_name)
models = {}
models[model_name] = model
else: #model != None
print("Already built model is passed")
if model_name == 'Ensemble':
Boosting.validate_model(model)
models = model.copy()
else:
models = {}
models[model_name] = model
#---------------------------------------
if model_name == 'Ensemble':
model_names = ['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace']
metric_names = ['cosine', 'euclidean', 'euclidean_l2']
elif model_name != 'Ensemble':
model_names = []
metric_names = []
model_names.append(model_name)
metric_names.append(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: #create representation.pkl from scratch
employees = []
for r, d, f in os.walk(
db_path): # r=root, d=directories, f = files
for file in f:
if ('.jpg' in file.lower()) or ('.png' in file.lower()):
exact_path = r + "/" + file
employees.append(exact_path)
if len(employees) == 0:
raise ValueError(
"There is no image in ", db_path,
" folder! Validate .jpg or .png files exist in this path.")
#------------------------
#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]
instance = []
instance.append(employee)
for j in model_names:
custom_model = models[j]
#----------------------------------
#decide input shape
input_shape = functions.find_input_shape(custom_model)
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 = custom_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."
)
#----------------------------
#now, we got representations for facial database
if model_name != 'Ensemble':
df = pd.DataFrame(
representations,
columns=["identity",
"%s_representation" % (model_name)])
else: #ensemble learning
columns = ['identity']
[columns.append('%s_representation' % i) for i in model_names]
df = pd.DataFrame(representations, columns=columns)
df_base = df.copy(
) #df will be filtered in each img. we will restore it for the next item.
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
for j in model_names:
custom_model = models[j]
#--------------------------------
#decide input shape
input_shape = functions.find_input_shape(custom_model)
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 = custom_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 model_name == 'Ensemble' and j == 'OpenFace' and k == 'euclidean':
continue
else:
df["%s_%s" % (j, k)] = distances
if model_name != 'Ensemble':
threshold = dst.findThreshold(j, k)
df = df.drop(columns=["%s_representation" % (j)])
df = df[df["%s_%s" % (j, k)] <= threshold]
df = df.sort_values(
by=["%s_%s" % (j, k)],
ascending=True).reset_index(drop=True)
resp_obj.append(df)
df = df_base.copy(
) #restore df for the next iteration
#----------------------------------
if model_name == 'Ensemble':
feature_names = []
for j in model_names:
for k in metric_names:
if model_name == 'Ensemble' and j == 'OpenFace' and k == 'euclidean':
continue
else:
feature = '%s_%s' % (j, k)
feature_names.append(feature)
#print(df.head())
x = df[feature_names].values
#--------------------------------------
boosted_tree = Boosting.build_gbm()
y = boosted_tree.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
#----------------------------------
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='mtcnn'):
tic = time.time()
img_list, bulkProcess = initialize_input(img1_path, img2_path)
functions.initialize_detector(detector_backend=detector_backend)
resp_objects = []
#--------------------------------
if model_name == 'Ensemble':
model_names = ["VGG-Face", "Facenet", "OpenFace", "DeepFace"]
metrics = ["cosine", "euclidean", "euclidean_l2"]
else:
model_names = []
metrics = []
model_names.append(model_name)
metrics.append(distance_metric)
#--------------------------------
if model == None:
if model_name == 'Ensemble':
models = Boosting.loadModel()
else:
model = build_model(model_name)
models = {}
models[model_name] = model
else:
if model_name == 'Ensemble':
Boosting.validate_model(model)
else:
models = {}
models[model_name] = model
#------------------------------
#calling deepface in a for loop causes lots of progress bars. this prevents it.
disable_option = False if len(img_list) > 1 else True
pbar = tqdm(range(0, len(img_list)),
desc='Verification',
disable=disable_option)
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 = []
for i in model_names:
custom_model = models[i]
#decide input shape
input_shape = functions.find_input_shape(custom_model)
input_shape_x = input_shape[0]
input_shape_y = input_shape[1]
#----------------------
#detect 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 = custom_model.predict(img1)[0, :]
img2_representation = custom_model.predict(img2)[0, :]
#----------------------
#find distances between embeddings
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))
else:
raise ValueError("Invalid distance_metric passed - ",
distance_metric)
#----------------------
#decision
if model_name != 'Ensemble':
threshold = dst.findThreshold(i, j)
if distance <= threshold:
identified = True
else:
identified = False
resp_obj = {
"verified": identified,
"distance": distance,
"max_threshold_to_verify": threshold,
"model": model_name,
"similarity_metric": distance_metric
}
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
return resp_obj
else: #Ensemble
#this returns same with OpenFace - euclidean_l2
if i == 'OpenFace' and j == 'euclidean':
continue
else:
ensemble_features.append(distance)
#----------------------
if model_name == 'Ensemble':
boosted_tree = Boosting.build_gbm()
prediction = boosted_tree.predict(
np.expand_dims(np.array(ensemble_features), axis=0))[0]
verified = np.argmax(prediction) == 1
score = prediction[np.argmax(prediction)]
resp_obj = {
"verified": verified,
"score": score,
"distance": ensemble_features,
"model": ["VGG-Face", "Facenet", "OpenFace", "DeepFace"],
"similarity_metric":
["cosine", "euclidean", "euclidean_l2"]
}
if bulkProcess == True:
resp_objects.append(resp_obj)
else:
return resp_obj
#----------------------
else:
raise ValueError("Invalid arguments passed to verify function: ",
instance)
#-------------------------
toc = time.time()
if bulkProcess == True:
resp_obj = {}
for i in range(0, len(resp_objects)):
resp_item = resp_objects[i]
resp_obj["pair_%d" % (i + 1)] = resp_item
return resp_obj
