faceNet.compile(optimizer='adam', loss=loss_triplet, metrics=['accuracy'])
faceNet=load_weights_from_FaceNet(faceNet)
debug(" weights are loaded from the csv files")
'''
MTCNN face detection
'''
#threshold = [0.6,0.6,0.7]
debug("Loading Deep face Detector (MTCNN) recognition model ....")
threshold = [0.3,0.7,0.7]
faceDetector = mtcnn()
debug("Loading Registered Persons faces encodings and index files generated with registerPerson.py ....")
REG_PERSONS_PATH = './images/registeredfaces'
HDF5_FACE_DATASET_NAME = "registeredFaces.h5"
hdf5_dataset_fullName = os.path.join(REG_PERSONS_PATH, HDF5_FACE_DATASET_NAME)
hdf5_file = h5py.File(hdf5_dataset_fullName, 'r')
index_dic = hdf5_file["index_dic"][:]
reg_faces_encodings = hdf5_file["faces_encoding"][:]
def create_hdf5_facedataset(in_images_folder_path,
out_hdf5_dataset_fullPath_name, faceNet):
'''
Create hdf5 face dataset by registering each person face.
The dataset contains the face images in opencv format, each image encodings obtained
using faceNet, and labels/person names
Input:
in_images_folder_path: path to a folder where each person images are stored subfolders
we assume that the subfolders, name represent face identity, on this path
contain images of a specific invidividual only, image of a person contains only face
out_hdf5_dataset_fullName: full path of the dataset to be saved
faceNet deep faceNet keras model
'''
person_subfolders = []
for p in os.listdir(in_images_folder_path):
ppath = os.path.join(in_images_folder_path, p)
if os.path.isdir(ppath):
person_subfolders.append(ppath)
face_image_paths = []
for i, person_subfolder in enumerate(person_subfolders):
for filename in os.listdir(person_subfolder):
img_path = os.path.join(person_subfolder, filename)
if filename.endswith('jpg'):
face_image_paths.append(img_path)
#person_name = os.path.splitext(os.path.dirname(img_path).split('/')[-1] )[0]
#print(person_name)
print("Total face images", len(face_image_paths))
image_shape = (len(face_image_paths), 96, 96, 3)
encod_shape = (len(face_image_paths), 128)
# open hdf5 file and create dataset
hdf5_file = h5py.File(out_hdf5_dataset_fullPath_name, mode='w')
#hdf5_file.create_dataset("faces_encoding", shape=encod_shape, dtype=np.float32)
# create resizable dataset as expected there may be any face in the training face images
hdf5_file.create_dataset("faces_encoding", (3000, 128),
maxshape=(None, 128),
dtype=np.float32)
dt = h5py.special_dtype(vlen=str)
#hdf5_file.create_dataset("index_dic", shape=(len(face_image_paths),), dtype=dt)
hdf5_file.create_dataset("index_dic", (3000, ),
maxshape=(None, ),
dtype=dt)
#hdf5_file.create_dataset("face_imgs_cv", shape=image_shape,dtype=np.uint8)
hdf5_file.create_dataset("face_imgs_cv", (3000, 96, 96, 3),
maxshape=(None, 96, 96, 3),
dtype=np.uint8)
# define throshod for facedetection and load mtcnn detector
threshold = [0.3, 0.6, 0.7]
faceDetector_mtcnn = mtcnn()
# now process each person images one by one and encode them using the faceNet model
# we will stored each encodings in face_encodings and their corresponding labels in index dictionary
img_cnt = -1
for image_path in face_image_paths:
print("encoding face detected in : {}".format(image_path))
image_cv = cv2.imread(image_path, 1)
img_draw, face_imgs, face_bboxes, faces_landmarks = extract_draw_faces(
faceDetector_mtcnn, image_cv, threshold)
if len(face_imgs) == 0:
continue
img_cnt += 1
lndmrks = np.array(faces_landmarks[0])
person_name = os.path.splitext(
os.path.dirname(image_path).split('/')[-1])[0]
#aligned_face_cv, aligned_face_lndmarks = normalize_faces_landmarks(out_img_size=(96,96), in_img=face_imgs[0], landmarks=lndmrks)
aligned_face_cv, aligned_face_lndmarks = align_face(out_img_size=(96,
96),
in_img=image_cv,
landmarks=lndmrks)
f_encoding = img_to_encoding(aligned_face_cv, faceNet)
print(f_encoding.shape)
#im[None].shape ==>(1, 96, 96, 3)
# writing data into dataset
print("img_cnt", img_cnt)
hdf5_file["face_imgs_cv"][img_cnt, ...] = aligned_face_cv[None]
hdf5_file["faces_encoding"][img_cnt, ...] = f_encoding
hdf5_file["index_dic"][img_cnt, ...] = person_name
## flip face vertical
img_cnt += 1
print("img_cnt", img_cnt)
#flip_aligned_face_cv = cv2.flip(aligned_face_cv,1)
#flip_lndmrks = np.flip(lndmrks, 1)
print(lndmrks)
flip_lndmrks = np.multiply(
np.subtract(lndmrks, [image_cv.shape[1], 0]), [-1, 1])
# after flip left and right position of eye changes
print(flip_lndmrks)
tmp = flip_lndmrks[0].copy()
flip_lndmrks[0] = flip_lndmrks[1].copy()
flip_lndmrks[1] = tmp.copy()
tmp = flip_lndmrks[3].copy()
flip_lndmrks[3] = flip_lndmrks[4].copy()
flip_lndmrks[3] = tmp.copy()
print(flip_lndmrks)
flip_image_cv = cv2.flip(image_cv, 1)
flip_aligned_face_cv, _ = align_face(out_img_size=(96, 96),
in_img=flip_image_cv,
landmarks=flip_lndmrks)
flip_f_encoding = img_to_encoding(flip_aligned_face_cv, faceNet)
# writing data into dataset
hdf5_file["face_imgs_cv"][img_cnt, ...] = flip_aligned_face_cv[None]
hdf5_file["faces_encoding"][img_cnt, ...] = flip_f_encoding
hdf5_file["index_dic"][img_cnt, ...] = person_name
## draw on images
face_lndmrk_draw = face_imgs[0].copy()
cv2.putText(face_lndmrk_draw, '1', (lndmrks[0][0], lndmrks[0][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[0][0], lndmrks[0][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '2', (lndmrks[1][0], lndmrks[1][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[1][0], lndmrks[1][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '3', (lndmrks[2][0], lndmrks[2][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[2][0], lndmrks[2][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '4', (lndmrks[3][0], lndmrks[3][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[3][0], lndmrks[3][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '5', (lndmrks[4][0], lndmrks[4][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[4][0], lndmrks[4][1]), 2,
(0, 255, 0))
cv2.imshow("face", face_lndmrk_draw)
aligned_face_draw = aligned_face_cv.copy()
cv2.putText(aligned_face_draw, '1',
(aligned_face_lndmarks[0][0], aligned_face_lndmarks[0][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(aligned_face_draw,
(aligned_face_lndmarks[0][0], aligned_face_lndmarks[0][1]),
2, (0, 255, 0))
cv2.putText(aligned_face_draw, '2',
(aligned_face_lndmarks[1][0], aligned_face_lndmarks[1][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(aligned_face_draw,
(aligned_face_lndmarks[1][0], aligned_face_lndmarks[1][1]),
2, (0, 255, 0))
cv2.imshow("aligned", aligned_face_draw)
cv2.imshow("face image", img_draw)
debug("face image of {}".format(person_name))
if (cv2.waitKey(100) == ord('q')):
break
# resize datasets according to total count img_cnt
hdf5_file["faces_encoding"].resize((img_cnt, 128))
hdf5_file["index_dic"].resize((img_cnt, ))
hdf5_file["face_imgs_cv"].resize((img_cnt, 96, 96, 3))
hdf5_file.close()
def save_encoded_faces_pickle(images_path, out_pic_file_path, faceNet):
'''
load face images from the images_path, detect faces, encode them and save the results pickle file
'''
threshold = [0.3, 0.6, 0.7]
faceDetector_mtcnn = mtcnn()
# prepare our registered people data
# assuming images folder contain individual images in subfolders
# each person images are put in corresponding subfolders, and each image of a person contains only face
person_subfolders = []
for p in os.listdir(images_path):
ppath = os.path.join(images_path, p)
if os.path.isdir(ppath):
person_subfolders.append(ppath)
#initial person name label Map
name_label_map = {}
# integer values of each person label
labels = []
person_image_paths = []
for i, person_subfolder in enumerate(person_subfolders):
for p in os.listdir(person_subfolder):
ppath = os.path.join(person_subfolder, p)
if p.endswith('jpg'):
person_image_paths.append(ppath)
labels.append(i)
name_label_map[p] = person_subfolder
# now process each person images one by one and encode them using the faceNet model
# we will stored each encodings in face_encodings and their corresponding labels in index dictionary
index_dic = {}
i = 0
faces_encoding = None
for image_path in person_image_paths:
debug("encoding face detected in : {}".format(image_path))
image_cv = cv2.imread(image_path, 1)
img_draw, face_imgs, face_bboxes, faces_landmarks = extract_draw_faces(
faceDetector_mtcnn, image_cv, threshold)
cv2.imshow("face image", img_draw)
if len(face_imgs) == 0:
continue
face_lndmrk_draw = face_imgs[0].copy()
lndmrks = np.array(faces_landmarks[0])
cv2.putText(face_lndmrk_draw, '1', (lndmrks[0][0], lndmrks[0][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[0][0], lndmrks[0][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '2', (lndmrks[1][0], lndmrks[1][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[1][0], lndmrks[1][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '3', (lndmrks[2][0], lndmrks[2][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[2][0], lndmrks[2][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '4', (lndmrks[3][0], lndmrks[3][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[3][0], lndmrks[3][1]), 2,
(0, 255, 0))
cv2.putText(face_lndmrk_draw, '5', (lndmrks[4][0], lndmrks[4][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(face_lndmrk_draw, (lndmrks[4][0], lndmrks[4][1]), 2,
(0, 255, 0))
cv2.imshow("face", face_lndmrk_draw)
#face_cv = cv2.resize(face_imgs[0], (96,96), interpolation=cv2.INTER_CUBIC)
#cv2.imshow("face 96x96", face_cv)
#aligned_face_cv, aligned_face_lndmarks = normalize_faces_landmarks(out_img_size=(96,96), in_img=face_imgs[0], landmarks=lndmrks)
#aligned_face_cv, aligned_face_lndmarks = align_face(out_img_size=(96,96), in_img=face_imgs[0], landmarks=lndmrks)
aligned_face_cv, aligned_face_lndmarks = align_face(out_img_size=(96,
96),
in_img=image_cv,
landmarks=lndmrks)
aligned_face_draw = aligned_face_cv.copy()
cv2.putText(aligned_face_draw, '1',
(aligned_face_lndmarks[0][0], aligned_face_lndmarks[0][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(aligned_face_draw,
(aligned_face_lndmarks[0][0], aligned_face_lndmarks[0][1]),
2, (0, 255, 0))
cv2.putText(aligned_face_draw, '2',
(aligned_face_lndmarks[1][0], aligned_face_lndmarks[1][1]),
cv2.FONT_ITALIC, 0.4, (0, 0, 255), 1)
cv2.circle(aligned_face_draw,
(aligned_face_lndmarks[1][0], aligned_face_lndmarks[1][1]),
2, (0, 255, 0))
cv2.imshow("aligned", aligned_face_draw)
cv2.waitKey(0)
# we have assumed that a single image will have only the face of the person
# compute the encodings
#f_encoding = img_to_encoding(face_cv, faceNet)
f_encoding = img_to_encoding(aligned_face_cv, faceNet)
if faces_encoding is None:
faces_encoding = f_encoding
else:
faces_encoding = np.concatenate((faces_encoding, f_encoding),
axis=0)
# save the label for this face in index_dic
# later, this will be used for verification or identification of a person
index_dic[i] = image_path
i = i + 1
# save the face encodings and label index dict
np.save(os.path.join(out_pic_file_path, 'faces_encoding.npy'),
faces_encoding)
with open(os.path.join(out_pic_file_path, 'index_dic.pkl'), 'wb') as f:
cPickle.dump(index_dic, f)
def build_camera(self, camera_id, path_name):
print(
"Loading Deep Face Detector(MTCNN) recognition model ............")
threshold = [0.6, 0.6, 0.7]
FaceDetector = mtcnn()
print(
"Deep Face Detection.............................................")
# 读取dataset数据集下的子文件夹名称
name_list = read_name_list(path_name)
# 打开摄像头并开始读取画面
# 捕获指定摄像头的实时视频流
cap = cv2.VideoCapture(camera_id)
success, frame = cap.read()
while True:
success, frame = cap.read()
thickness = (frame.shape[0] + frame.shape[1]) // 350
faceRects = FaceDetector.detectFace(frame, threshold)
draw = frame.copy()
#faceRects存的是每个矩形框的中心的坐标以及5个特征点坐标
for faceRect in faceRects:
if faceRect is not None:
W = -int(faceRect[0]) + int(faceRect[2])
H = -int(faceRect[1]) + int(faceRect[3])
paddingH = 0.02 * H
paddingW = 0.01 * W
crop_img = frame[int(faceRect[1] +
paddingH):int(faceRect[3] - paddingH),
int(faceRect[0] -
paddingW):int(faceRect[2] + paddingW)]
print(
"Face Recognition................................................"
)
label, prob = self.model.face_predict(crop_img)
# 如果模型认为概率高于50%则显示为模型中已有的label
if prob > 0.7:
show_name = name_list[label]
else:
show_name = 'Stranger'
# 显示名字，字体，字号为1，颜色为粉色，字的线宽为2
person_tag = "%s: %.2f" % (show_name, prob)
text_end = (int(faceRect[0]) + len(person_tag) * 10,
int(faceRect[1]) - 20)
text_start = (max(int(faceRect[0]),
10), max(int(faceRect[1]), 10))
cv2.rectangle(draw, text_end, text_start, (0, 255, 0), -1,
cv2.LINE_AA)
cv2.putText(draw, person_tag, text_start,
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 255),
1)
#crop_img = cv2.cvtColor(crop_img, cv2.COLOR_RGB2GRAY)
if crop_img is None:
continue
if crop_img.shape[0] < 0 or crop_img.shape[1] < 0:
continue
# 在人脸区域画一个正方形出来
for i in range(thickness):
start = (int(faceRect[0]) + i, int(faceRect[1]) + i)
end = (int(faceRect[2] - i), int(faceRect[3]) - i)
frame = cv2.rectangle(draw, start, end, (0, 255, 0), 1)
# 画出landmarks的
for i in range(5, 15, 2):
cv2.circle(draw,
(int(faceRect[i + 0]), int(faceRect[i + 1])), 2,
(0, 255, 0))
cv2.imshow("Camera", draw)
# 等待10毫秒看是否有按键输入
k = cv2.waitKey(10)
# 如果输入q则退出循环
if k & 0xFF == ord('q'):
break
# 释放摄像头并销毁所有窗口
cap.release()
cv2.destroyAllWindows()
return camera_id, path_name