基于python_opencv人脸录入、识别系统（应用dlib机器学习库）
近几年应用opencv机器学习方法识别人脸的技术成为了热潮，本人根据当今的识别技术与方法，历时四个多月开发出一套基于dlib机器学习库的识别项目。希望大家能一起交流学习。
项目英文名：Face recognition from camera with Dlib
文章目录
- 基于python_opencv人脸录入、识别系统（应用dlib机器学习库）
- **项目英文名：Face recognition from camera with Dlib**
- 1、项目功能介绍
- 2、项目运行截图
- 3、项目流程图
- 4、项目源码结构及模块化介绍（需要源码的朋友关注并私信我）
- 5、总结
1、项目功能介绍
- Tkinter 人脸录入界面, 支持录入时设置 (中文) 姓名；
- 调用摄像头进行人脸识别, 支持多张人脸同时识别；
- 定制显示名字, 可以写中文；
2、项目运行截图
下面直接上运行截图：
GUI界面运行结果： UI界面可以录入使用者的信息，并设置保存录入图片按钮
初次录入界面：
距离摄像头太近或太远会有提示：
中文识别界面运行结果： 识别信息包括开始录入时设置的名字，以及镜头下识别的人数
支持多人识别：
3、项目流程图
项目的流程图如下：
4、项目源码结构及模块化介绍（需要源码的朋友关注并私信我）
项目源码的结构如下：
- get_faces_from_camera_tkinter.py：进行人脸信息采集录入, Tkinter GUI
- get_face_from_camera.py：进行人脸信息采集录入, OpenCV GUI
- features_extraction_to_csv.py：提取所有录入人脸数据存入
features_all.csv - face_reco_from_camera.py：调用摄像头进行实时人脸识别
- face_reco_from_camera_single_face.py：对于人脸数<=1, 调用摄像头进行实时人脸识别
- face_reco_from_camera_ot.py：利用 OT 算法, 调用摄像头进行实时人脸识别
Python详细源码模块化介绍：
人脸信息采集录入模块（get_face_from_camera.py）：
- 请注意存储人脸图片时, 矩形框不要超出摄像头范围, 要不然无法保存到本地;
- 超出会有 “out of range” 的提醒;
class Face_Register:
def __init__(self):
self.path_photos_from_camera = "data/data_faces_from_camera/"
self.font = cv2.FONT_ITALIC
self.existing_faces_cnt = 0 # 已录入的人脸计数器 / cnt for counting saved faces
self.ss_cnt = 0 # 录入 personX 人脸时图片计数器 / cnt for screen shots
self.current_frame_faces_cnt = 0 # 录入人脸计数器 / cnt for counting faces in current frame
self.save_flag = 1 # 之后用来控制是否保存图像的 flag / The flag to control if save
self.press_n_flag = 0 # 之后用来检查是否先按 'n' 再按 's' / The flag to check if press 'n' before 's'
# FPS
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.fps_show = 0
self.start_time = time.time()
# 新建保存人脸图像文件和数据 CSV 文件夹 / Mkdir for saving photos and csv
def pre_work_mkdir(self):
# 新建文件夹 / Create folders to save face images and csv
if os.path.isdir(self.path_photos_from_camera):
pass
else:
os.mkdir(self.path_photos_from_camera)
# 删除之前存的人脸数据文件夹 / Delete old face folders
def pre_work_del_old_face_folders(self):
# 删除之前存的人脸数据文件夹, 删除 "/data_faces_from_camera/person_x/"...
folders_rd = os.listdir(self.path_photos_from_camera)
for i in range(len(folders_rd)):
shutil.rmtree(self.path_photos_from_camera+folders_rd[i])
if os.path.isfile("data/features_all.csv"):
os.remove("data/features_all.csv")
# 如果有之前录入的人脸, 在之前 person_x 的序号按照 person_x+1 开始录入 / Start from person_x+1
def check_existing_faces_cnt(self):
if os.listdir("data/data_faces_from_camera/"):
# 获取已录入的最后一个人脸序号 / Get the order of latest person
person_list = os.listdir("data/data_faces_from_camera/")
person_num_list = []
for person in person_list:
person_num_list.append(int(person.split('_')[-1]))
self.existing_faces_cnt = max(person_num_list)
# 如果第一次存储或者没有之前录入的人脸, 按照 person_1 开始录入 / Start from person_1
else:
self.existing_faces_cnt = 0
# 更新 FPS / Update FPS of Video stream
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
# 生成的 cv2 window 上面添加说明文字 / PutText on cv2 window
def draw_note(self, img_rd):
# 添加说明 / Add some notes
cv2.putText(img_rd, "Face Register", (20, 40), self.font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps_show.__round__(2)), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(self.current_frame_faces_cnt), (20, 140), self.font, 0.8, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(img_rd, "N: Create face folder", (20, 350), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "S: Save current face", (20, 400), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
# 获取人脸 / Main process of face detection and saving
def process(self, stream):
# 1. 新建储存人脸图像文件目录 / Create folders to save photos
self.pre_work_mkdir()
# 2. 删除 "/data/data_faces_from_camera" 中已有人脸图像文件
# / Uncomment if want to delete the saved faces and start from person_1
# if os.path.isdir(self.path_photos_from_camera):
# self.pre_work_del_old_face_folders()
# 3. 检查 "/data/data_faces_from_camera" 中已有人脸文件
self.check_existing_faces_cnt()
while stream.isOpened():
flag, img_rd = stream.read() # Get camera video stream
kk = cv2.waitKey(1)
faces = detector(img_rd, 0) # Use Dlib face detector
# 4. 按下 'n' 新建存储人脸的文件夹 / Press 'n' to create the folders for saving faces
if kk == ord('n'):
self.existing_faces_cnt += 1
current_face_dir = self.path_photos_from_camera + "person_" + str(self.existing_faces_cnt)
os.makedirs(current_face_dir)
logging.info("\n%-40s %s", "新建的人脸文件夹 / Create folders:", current_face_dir)
self.ss_cnt = 0 # 将人脸计数器清零 / Clear the cnt of screen shots
self.press_n_flag = 1 # 已经按下 'n' / Pressed 'n' already
# 5. 检测到人脸 / Face detected
if len(faces) != 0:
# 矩形框 / Show the ROI of faces
for k, d in enumerate(faces):
# 计算矩形框大小 / Compute the size of rectangle box
height = (d.bottom() - d.top())
width = (d.right() - d.left())
hh = int(height/2)
ww = int(width/2)
# 6. 判断人脸矩形框是否超出 480x640 / If the size of ROI > 480x640
if (d.right()+ww) > 640 or (d.bottom()+hh > 480) or (d.left()-ww < 0) or (d.top()-hh < 0):
cv2.putText(img_rd, "OUT OF RANGE", (20, 300), self.font, 0.8, (0, 0, 255), 1, cv2.LINE_AA)
color_rectangle = (0, 0, 255)
save_flag = 0
if kk == ord('s'):
logging.warning("请调整位置 / Please adjust your position")
else:
color_rectangle = (255, 255, 255)
save_flag = 1
cv2.rectangle(img_rd,
tuple([d.left() - ww, d.top() - hh]),
tuple([d.right() + ww, d.bottom() + hh]),
color_rectangle, 2)
# 7. 根据人脸大小生成空的图像 / Create blank image according to the size of face detected
img_blank = np.zeros((int(height*2), width*2, 3), np.uint8)
if save_flag:
# 8. 按下 's' 保存摄像头中的人脸到本地 / Press 's' to save faces into local images
if kk == ord('s'):
# 检查有没有先按'n'新建文件夹 / Check if you have pressed 'n'
if self.press_n_flag:
self.ss_cnt += 1
for ii in range(height*2):
for jj in range(width*2):
img_blank[ii][jj] = img_rd[d.top()-hh + ii][d.left()-ww + jj]
cv2.imwrite(current_face_dir + "/img_face_" + str(self.ss_cnt) + ".jpg", img_blank)
logging.info("%-40s %s/img_face_%s.jpg", "写入本地 / Save into：",
str(current_face_dir), str(self.ss_cnt))
else:
logging.warning("请先按 'N' 来建文件夹, 按 'S' / Please press 'N' and press 'S'")
self.current_frame_faces_cnt = len(faces)
# 9. 生成的窗口添加说明文字 / Add note on cv2 window
self.draw_note(img_rd)
# 10. 按下 'q' 键退出 / Press 'q' to exit
if kk == ord('q'):
break
# 11. Update FPS
self.update_fps()
cv2.namedWindow("camera", 1)
cv2.imshow("camera", img_rd)
def run(self):
# cap = cv2.VideoCapture("video.mp4") # Get video stream from video file
cap = cv2.VideoCapture(0) # Get video stream from camera
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
logging.basicConfig(level=logging.INFO)
Face_Register_con = Face_Register()
Face_Register_con.run()
if __name__ == '__main__':
main()
进行人脸信息采集录入 Tkinter GUI（get_faces_from_camera_tkinter.py）：
class Face_Register:
def __init__(self):
self.current_frame_faces_cnt = 0 # 当前帧中人脸计数器 / cnt for counting faces in current frame
self.existing_faces_cnt = 0 # 已录入的人脸计数器 / cnt for counting saved faces
self.ss_cnt = 0 # 录入 person_n 人脸时图片计数器 / cnt for screen shots
# Tkinter GUI
self.win = tk.Tk()
self.win.title("Face Register @coneypo")
# PLease modify window size here if needed
self.win.geometry("1300x550")
# GUI left part
self.frame_left_camera = tk.Frame(self.win)
self.label = tk.Label(self.win)
self.label.pack(side=tk.LEFT)
self.frame_left_camera.pack()
# GUI right part
self.frame_right_info = tk.Frame(self.win)
self.label_cnt_face_in_database = tk.Label(self.frame_right_info, text=str(self.existing_faces_cnt))
self.label_fps_info = tk.Label(self.frame_right_info, text="")
self.input_name = tk.Entry(self.frame_right_info)
self.input_name_char = ""
self.label_warning = tk.Label(self.frame_right_info)
self.label_face_cnt = tk.Label(self.frame_right_info, text="Faces in current frame: ")
self.log_all = tk.Label(self.frame_right_info)
self.font_title = tkFont.Font(family='Helvetica', size=20, weight='bold')
self.font_step_title = tkFont.Font(family='Helvetica', size=15, weight='bold')
self.font_warning = tkFont.Font(family='Helvetica', size=15, weight='bold')
self.path_photos_from_camera = "data/data_faces_from_camera/"
self.current_face_dir = ""
self.font = cv2.FONT_ITALIC
# Current frame and face ROI position
self.current_frame = np.ndarray
self.face_ROI_image = np.ndarray
self.face_ROI_width_start = 0
self.face_ROI_height_start = 0
self.face_ROI_width = 0
self.face_ROI_height = 0
self.ww = 0
self.hh = 0
self.out_of_range_flag = False
self.face_folder_created_flag = False
# FPS
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.fps_show = 0
self.start_time = time.time()
self.cap = cv2.VideoCapture(0) # Get video stream from camera
# self.cap = cv2.VideoCapture("test.mp4") # Input local video
# 删除之前存的人脸数据文件夹 / Delete old face folders
def GUI_clear_data(self):
# 删除之前存的人脸数据文件夹, 删除 "/data_faces_from_camera/person_x/"...
folders_rd = os.listdir(self.path_photos_from_camera)
for i in range(len(folders_rd)):
shutil.rmtree(self.path_photos_from_camera + folders_rd[i])
if os.path.isfile("data/features_all.csv"):
os.remove("data/features_all.csv")
self.label_cnt_face_in_database['text'] = "0"
self.existing_faces_cnt = 0
self.log_all["text"] = "Face images and `features_all.csv` removed!"
def GUI_get_input_name(self):
self.input_name_char = self.input_name.get()
self.create_face_folder()
self.label_cnt_face_in_database['text'] = str(self.existing_faces_cnt)
def GUI_info(self):
tk.Label(self.frame_right_info,
text="Face register",
font=self.font_title).grid(row=0, column=0, columnspan=3, sticky=tk.W, padx=2, pady=20)
tk.Label(self.frame_right_info,
text="FPS: ").grid(row=1, column=0, columnspan=2, sticky=tk.W, padx=5, pady=2)
self.label_fps_info.grid(row=1, column=2, sticky=tk.W, padx=5, pady=2)
tk.Label(self.frame_right_info,
text="Faces in database: ").grid(row=2, column=0, columnspan=2, sticky=tk.W, padx=5, pady=2)
self.label_cnt_face_in_database.grid(row=2, column=2, columnspan=3, sticky=tk.W, padx=5, pady=2)
tk.Label(self.frame_right_info,
text="Faces in current frame: ").grid(row=3, column=0, columnspan=2, sticky=tk.W, padx=5, pady=2)
self.label_face_cnt.grid(row=3, column=2, columnspan=3, sticky=tk.W, padx=5, pady=2)
self.label_warning.grid(row=4, column=0, columnspan=3, sticky=tk.W, padx=5, pady=2)
# Step 1: Clear old data
tk.Label(self.frame_right_info,
font=self.font_step_title,
text="Step 1: Clear face photos").grid(row=5, column=0, columnspan=2, sticky=tk.W, padx=5, pady=20)
tk.Button(self.frame_right_info,
text='Clear',
command=self.GUI_clear_data).grid(row=6, column=0, columnspan=3, sticky=tk.W, padx=5, pady=2)
# Step 2: Input name and create folders for face
tk.Label(self.frame_right_info,
font=self.font_step_title,
text="Step 2: Input name").grid(row=7, column=0, columnspan=2, sticky=tk.W, padx=5, pady=20)
tk.Label(self.frame_right_info, text="Name: ").grid(row=8, column=0, sticky=tk.W, padx=5, pady=0)
self.input_name.grid(row=8, column=1, sticky=tk.W, padx=0, pady=2)
tk.Button(self.frame_right_info,
text='Input',
command=self.GUI_get_input_name).grid(row=8, column=2, padx=5)
# Step 3: Save current face in frame
tk.Label(self.frame_right_info,
font=self.font_step_title,
text="Step 3: Save face image").grid(row=9, column=0, columnspan=2, sticky=tk.W, padx=5, pady=20)
tk.Button(self.frame_right_info,
text='Save current face',
command=self.save_current_face).grid(row=10, column=0, columnspan=3, sticky=tk.W)
# Show log in GUI
self.log_all.grid(row=11, column=0, columnspan=20, sticky=tk.W, padx=5, pady=20)
self.frame_right_info.pack()
# 新建保存人脸图像文件和数据 CSV 文件夹 / Mkdir for saving photos and csv
def pre_work_mkdir(self):
# 新建文件夹 / Create folders to save face images and csv
if os.path.isdir(self.path_photos_from_camera):
pass
else:
os.mkdir(self.path_photos_from_camera)
# 如果有之前录入的人脸, 在之前 person_x 的序号按照 person_x+1 开始录入 / Start from person_x+1
def check_existing_faces_cnt(self):
if os.listdir("data/data_faces_from_camera/"):
# 获取已录入的最后一个人脸序号 / Get the order of latest person
person_list = os.listdir("data/data_faces_from_camera/")
person_num_list = []
for person in person_list:
person_order = person.split('_')[1].split('_')[0]
person_num_list.append(int(person_order))
self.existing_faces_cnt = max(person_num_list)
# 如果第一次存储或者没有之前录入的人脸, 按照 person_1 开始录入 / Start from person_1
else:
self.existing_faces_cnt = 0
# 更新 FPS / Update FPS of Video stream
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
self.label_fps_info["text"] = str(self.fps.__round__(2))
def create_face_folder(self):
# 新建存储人脸的文件夹 / Create the folders for saving faces
self.existing_faces_cnt += 1
if self.input_name_char:
self.current_face_dir = self.path_photos_from_camera + \
"person_" + str(self.existing_faces_cnt) + "_" + \
self.input_name_char
else:
self.current_face_dir = self.path_photos_from_camera + \
"person_" + str(self.existing_faces_cnt)
os.makedirs(self.current_face_dir)
self.log_all["text"] = "\"" + self.current_face_dir + "/\" created!"
logging.info("\n%-40s %s", "新建的人脸文件夹 / Create folders:", self.current_face_dir)
self.ss_cnt = 0 # 将人脸计数器清零 / Clear the cnt of screen shots
self.face_folder_created_flag = True # Face folder already created
def save_current_face(self):
if self.face_folder_created_flag:
if self.current_frame_faces_cnt == 1:
if not self.out_of_range_flag:
self.ss_cnt += 1
# 根据人脸大小生成空的图像 / Create blank image according to the size of face detected
self.face_ROI_image = np.zeros((int(self.face_ROI_height * 2), self.face_ROI_width * 2, 3),
np.uint8)
for ii in range(self.face_ROI_height * 2):
for jj in range(self.face_ROI_width * 2):
self.face_ROI_image[ii][jj] = self.current_frame[self.face_ROI_height_start - self.hh + ii][
self.face_ROI_width_start - self.ww + jj]
self.log_all["text"] = "\"" + self.current_face_dir + "/img_face_" + str(
self.ss_cnt) + ".jpg\"" + " saved!"
self.face_ROI_image = cv2.cvtColor(self.face_ROI_image, cv2.COLOR_BGR2RGB)
cv2.imwrite(self.current_face_dir + "/img_face_" + str(self.ss_cnt) + ".jpg", self.face_ROI_image)
logging.info("%-40s %s/img_face_%s.jpg", "写入本地 / Save into：",
str(self.current_face_dir), str(self.ss_cnt) + ".jpg")
else:
self.log_all["text"] = "Please do not out of range!"
else:
self.log_all["text"] = "No face in current frame!"
else:
self.log_all["text"] = "Please run step 2!"
def get_frame(self):
try:
if self.cap.isOpened():
ret, frame = self.cap.read()
return ret, cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
except:
print("Error: No video input!!!")
# 获取人脸 / Main process of face detection and saving
def process(self):
ret, self.current_frame = self.get_frame()
faces = detector(self.current_frame, 0)
# Get frame
if ret:
self.update_fps()
self.label_face_cnt["text"] = str(len(faces))
# 检测到人脸 / Face detected
if len(faces) != 0:
# 矩形框 / Show the ROI of faces
for k, d in enumerate(faces):
self.face_ROI_width_start = d.left()
self.face_ROI_height_start = d.top()
# 计算矩形框大小 / Compute the size of rectangle box
self.face_ROI_height = (d.bottom() - d.top())
self.face_ROI_width = (d.right() - d.left())
self.hh = int(self.face_ROI_height / 2)
self.ww = int(self.face_ROI_width / 2)
# 判断人脸矩形框是否超出 480x640 / If the size of ROI > 480x640
if (d.right() + self.ww) > 640 or (d.bottom() + self.hh > 480) or (d.left() - self.ww < 0) or (
d.top() - self.hh < 0):
self.label_warning["text"] = "OUT OF RANGE"
self.label_warning['fg'] = 'red'
self.out_of_range_flag = True
color_rectangle = (255, 0, 0)
else:
self.out_of_range_flag = False
self.label_warning["text"] = ""
color_rectangle = (255, 255, 255)
self.current_frame = cv2.rectangle(self.current_frame,
tuple([d.left() - self.ww, d.top() - self.hh]),
tuple([d.right() + self.ww, d.bottom() + self.hh]),
color_rectangle, 2)
self.current_frame_faces_cnt = len(faces)
# Convert PIL.Image.Image to PIL.Image.PhotoImage
img_Image = Image.fromarray(self.current_frame)
img_PhotoImage = ImageTk.PhotoImage(image=img_Image)
self.label.img_tk = img_PhotoImage
self.label.configure(image=img_PhotoImage)
# Refresh frame
self.win.after(20, self.process)
def run(self):
self.pre_work_mkdir()
self.check_existing_faces_cnt()
self.GUI_info()
self.process()
self.win.mainloop()
def main():
logging.basicConfig(level=logging.INFO)
Face_Register_con = Face_Register()
Face_Register_con.run()
if __name__ == '__main__':
main()
提取人脸数据存入 CSV（features_extraction_to_csv.py）：
- 会生成一个存储所有特征人脸数据的
features_all.csv - Size:
n*129
# 要读取人脸图像文件的路径 / Path of cropped faces
path_images_from_camera = "data/data_faces_from_camera/"
# Dlib 正向人脸检测器 / Use frontal face detector of Dlib
detector = dlib.get_frontal_face_detector()
# Dlib 人脸 landmark 特征点检测器 / Get face landmarks
predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat')
# Dlib Resnet 人脸识别模型，提取 128D 的特征矢量 / Use Dlib resnet50 model to get 128D face descriptor
face_reco_model = dlib.face_recognition_model_v1("data/data_dlib/dlib_face_recognition_resnet_model_v1.dat")
# 返回单张图像的 128D 特征 / Return 128D features for single image
# Input: path_img <class 'str'>
# Output: face_descriptor <class 'dlib.vector'>
def return_128d_features(path_img):
img_rd = cv2.imread(path_img)
faces = detector(img_rd, 1)
logging.info("%-40s %-20s", "检测到人脸的图像 / Image with faces detected:", path_img)
# 因为有可能截下来的人脸再去检测，检测不出来人脸了, 所以要确保是 检测到人脸的人脸图像拿去算特征
# For photos of faces saved, we need to make sure that we can detect faces from the cropped images
if len(faces) != 0:
shape = predictor(img_rd, faces[0])
face_descriptor = face_reco_model.compute_face_descriptor(img_rd, shape)
else:
face_descriptor = 0
logging.warning("no face")
return face_descriptor
# 返回 personX 的 128D 特征均值 / Return the mean value of 128D face descriptor for person X
# Input: path_face_personX <class 'str'>
# Output: features_mean_personX <class 'numpy.ndarray'>
def return_features_mean_personX(path_face_personX):
features_list_personX = []
photos_list = os.listdir(path_face_personX)
if photos_list:
for i in range(len(photos_list)):
# 调用 return_128d_features() 得到 128D 特征 / Get 128D features for single image of personX
logging.info("%-40s %-20s", "正在读的人脸图像 / Reading image:", path_face_personX + "/" + photos_list[i])
features_128d = return_128d_features(path_face_personX + "/" + photos_list[i])
# 遇到没有检测出人脸的图片跳过 / Jump if no face detected from image
if features_128d == 0:
i += 1
else:
features_list_personX.append(features_128d)
else:
logging.warning("文件夹内图像文件为空 / Warning: No images in%s/", path_face_personX)
# 计算 128D 特征的均值 / Compute the mean
# personX 的 N 张图像 x 128D -> 1 x 128D
if features_list_personX:
features_mean_personX = np.array(features_list_personX, dtype=object).mean(axis=0)
else:
features_mean_personX = np.zeros(128, dtype=object, order='C')
return features_mean_personX
def main():
logging.basicConfig(level=logging.INFO)
# 获取已录入的最后一个人脸序号 / Get the order of latest person
person_list = os.listdir("data/data_faces_from_camera/")
person_list.sort()
with open("data/features_all.csv", "w", newline="") as csvfile:
writer = csv.writer(csvfile)
for person in person_list:
# Get the mean/average features of face/personX, it will be a list with a length of 128D
logging.info("%sperson_%s", path_images_from_camera, person)
features_mean_personX = return_features_mean_personX(path_images_from_camera + person)
if len(person.split('_', 2)) == 2:
# "person_x"
person_name = person
else:
# "person_x_tom"
person_name = person.split('_', 2)[-1]
features_mean_personX = np.insert(features_mean_personX, 0, person_name, axis=0)
# features_mean_personX will be 129D, person name + 128 features
writer.writerow(features_mean_personX)
logging.info('\n')
logging.info("所有录入人脸数据存入 / Save all the features of faces registered into: data/features_all.csv")
if __name__ == '__main__':
main()
调用摄像头进行实时人脸识别（face_reco_from_camera.py）：
- 将捕获到的人脸数据和之前存的人脸数据进行对比计算欧式距离, 由此判断是否是同一个人;
class Face_Recognizer:
def __init__(self):
self.face_feature_known_list = [] # 用来存放所有录入人脸特征的数组 / Save the features of faces in database
self.face_name_known_list = [] # 存储录入人脸名字 / Save the name of faces in database
self.current_frame_face_cnt = 0 # 存储当前摄像头中捕获到的人脸数 / Counter for faces in current frame
self.current_frame_face_feature_list = [] # 存储当前摄像头中捕获到的人脸特征 / Features of faces in current frame
self.current_frame_face_name_list = [] # 存储当前摄像头中捕获到的所有人脸的名字 / Names of faces in current frame
self.current_frame_face_name_position_list = [] # 存储当前摄像头中捕获到的所有人脸的名字坐标 / Positions of faces in current frame
# Update FPS
self.fps = 0 # FPS of current frame
self.fps_show = 0 # FPS per second
self.frame_start_time = 0
self.frame_cnt = 0
self.start_time = time.time()
self.font = cv2.FONT_ITALIC
self.font_chinese = ImageFont.truetype("simsun.ttc", 30)
# 从 "features_all.csv" 读取录入人脸特征 / Read known faces from "features_all.csv"
def get_face_database(self):
if os.path.exists("data/features_all.csv"):
path_features_known_csv = "data/features_all.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
for i in range(csv_rd.shape[0]):
features_someone_arr = []
self.face_name_known_list.append(csv_rd.iloc[i][0])
for j in range(1, 129):
if csv_rd.iloc[i][j] == '':
features_someone_arr.append('0')
else:
features_someone_arr.append(csv_rd.iloc[i][j])
self.face_feature_known_list.append(features_someone_arr)
logging.info("Faces in Database：%d", len(self.face_feature_known_list))
return 1
else:
logging.warning("'features_all.csv' not found!")
logging.warning("Please run 'get_faces_from_camera.py' "
"and 'features_extraction_to_csv.py' before 'face_reco_from_camera.py'")
return 0
# 计算两个128D向量间的欧式距离 / Compute the e-distance between two 128D features
@staticmethod
def return_euclidean_distance(feature_1, feature_2):
feature_1 = np.array(feature_1)
feature_2 = np.array(feature_2)
dist = np.sqrt(np.sum(np.square(feature_1 - feature_2)))
return dist
# 更新 FPS / Update FPS of Video stream
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
# 生成的 cv2 window 上面添加说明文字 / PutText on cv2 window
def draw_note(self, img_rd):
cv2.putText(img_rd, "Face Recognizer", (20, 40), self.font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Frame: " + str(self.frame_cnt), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps_show.__round__(2)), (20, 130), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(self.current_frame_face_cnt), (20, 160), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
def draw_name(self, img_rd):
# 在人脸框下面写人脸名字 / Write names under rectangle
img = Image.fromarray(cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img)
for i in range(self.current_frame_face_cnt):
# cv2.putText(img_rd, self.current_frame_face_name_list[i], self.current_frame_face_name_position_list[i], self.font, 0.8, (0, 255, 255), 1, cv2.LINE_AA)
draw.text(xy=self.current_frame_face_name_position_list[i], text=self.current_frame_face_name_list[i], font=self.font_chinese,
fill=(255, 255, 0))
img_rd = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
return img_rd
# 修改显示人名 / Show names in chinese
def show_chinese_name(self):
# Default known name: person_1, person_2, person_3
if self.current_frame_face_cnt >= 1:
# 修改录入的人脸姓名 / Modify names in face_name_known_list to chinese name
self.face_name_known_list[0] = '张三'.encode('utf-8').decode()
# self.face_name_known_list[1] = '张四'.encode('utf-8').decode()
# 处理获取的视频流，进行人脸识别 / Face detection and recognition from input video stream
def process(self, stream):
# 1. 读取存放所有人脸特征的 csv / Read known faces from "features.all.csv"
if self.get_face_database():
while stream.isOpened():
self.frame_cnt += 1
logging.debug("Frame %d starts", self.frame_cnt)
flag, img_rd = stream.read()
faces = detector(img_rd, 0)
kk = cv2.waitKey(1)
# 按下 q 键退出 / Press 'q' to quit
if kk == ord('q'):
break
else:
self.draw_note(img_rd)
self.current_frame_face_feature_list = []
self.current_frame_face_cnt = 0
self.current_frame_face_name_position_list = []
self.current_frame_face_name_list = []
# 2. 检测到人脸 / Face detected in current frame
if len(faces) != 0:
# 3. 获取当前捕获到的图像的所有人脸的特征 / Compute the face descriptors for faces in current frame
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_face_feature_list.append(face_reco_model.compute_face_descriptor(img_rd, shape))
# 4. 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
logging.debug("For face %d in camera:", k+1)
# 先默认所有人不认识，是 unknown / Set the default names of faces with "unknown"
self.current_frame_face_name_list.append("unknown")
# 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_face_name_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# 5. 对于某张人脸，遍历所有存储的人脸特征
# For every faces detected, compare the faces in the database
current_frame_e_distance_list = []
for i in range(len(self.face_feature_known_list)):
# 如果 person_X 数据不为空
if str(self.face_feature_known_list[i][0]) != '0.0':
e_distance_tmp = self.return_euclidean_distance(self.current_frame_face_feature_list[k],
self.face_feature_known_list[i])
logging.debug(" With person %s, the e-distance is %f", str(i + 1), e_distance_tmp)
current_frame_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
current_frame_e_distance_list.append(999999999)
# 6. 寻找出最小的欧式距离匹配 / Find the one with minimum e-distance
similar_person_num = current_frame_e_distance_list.index(min(current_frame_e_distance_list))
logging.debug("Minimum e-distance with %s: %f", self.face_name_known_list[similar_person_num], min(current_frame_e_distance_list))
if min(current_frame_e_distance_list) < 0.4:
self.current_frame_face_name_list[k] = self.face_name_known_list[similar_person_num]
logging.debug("Face recognition result: %s", self.face_name_known_list[similar_person_num])
else:
logging.debug("Face recognition result: Unknown person")
logging.debug("\n")
# 矩形框 / Draw rectangle
for kk, d in enumerate(faces):
# 绘制矩形框
cv2.rectangle(img_rd, tuple([d.left(), d.top()]), tuple([d.right(), d.bottom()]),
(255, 255, 255), 2)
self.current_frame_face_cnt = len(faces)
# 7. 在这里更改显示的人名 / Modify name if needed
# self.show_chinese_name()
# 8. 写名字 / Draw name
img_with_name = self.draw_name(img_rd)
else:
img_with_name = img_rd
logging.debug("Faces in camera now: %s", self.current_frame_face_name_list)
cv2.imshow("camera", img_with_name)
# 9. 更新 FPS / Update stream FPS
self.update_fps()
logging.debug("Frame ends\n\n")
# OpenCV 调用摄像头并进行 process
def run(self):
# cap = cv2.VideoCapture("video.mp4") # Get video stream from video file
cap = cv2.VideoCapture(0) # Get video stream from camera
cap.set(3, 480) # 640x480
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
# logging.basicConfig(level=logging.DEBUG) # Set log level to 'logging.DEBUG' to print debug info of every frame
logging.basicConfig(level=logging.INFO)
Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run()
if __name__ == '__main__':
main()
对每一帧都进行检测+识别（face_reco_from_camera_single_face.py）：
- 针对于人脸数 <=1 的场景, 区别于
face_reco_from_camera.py(对每一帧都进行检测+识别), 只有人脸出现的时候进行识别
class Face_Recognizer:
def __init__(self):
self.font = cv2.FONT_ITALIC
self.font_chinese = ImageFont.truetype("simsun.ttc", 30)
# 统计 FPS / For FPS
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.fps_show = 0
self.start_time = time.time()
# 统计帧数 / cnt for frame
self.frame_cnt = 0
# 用来存储所有录入人脸特征的数组 / Save the features of faces in the database
self.features_known_list = []
# 用来存储录入人脸名字 / Save the name of faces in the database
self.face_name_known_list = []
# 用来存储上一帧和当前帧 ROI 的质心坐标 / List to save centroid positions of ROI in frame N-1 and N
self.last_frame_centroid_list = []
self.current_frame_centroid_list = []
# 用来存储当前帧检测出目标的名字 / List to save names of objects in current frame
self.current_frame_name_list = []
# 上一帧和当前帧中人脸数的计数器 / cnt for faces in frame N-1 and N
self.last_frame_faces_cnt = 0
self.current_frame_face_cnt = 0
# 用来存放进行识别时候对比的欧氏距离 / Save the e-distance for faceX when recognizing
self.current_frame_face_X_e_distance_list = []
# 存储当前摄像头中捕获到的所有人脸的坐标名字 / Save the positions and names of current faces captured
self.current_frame_face_position_list = []
# 存储当前摄像头中捕获到的人脸特征 / Save the features of people in current frame
self.current_frame_face_feature_list = []
# 控制再识别的后续帧数 / Reclassify after 'reclassify_interval' frames
# 如果识别出 "unknown" 的脸, 将在 reclassify_interval_cnt 计数到 reclassify_interval 后, 对于人脸进行重新识别
self.reclassify_interval_cnt = 0
self.reclassify_interval = 10
# 从 "features_all.csv" 读取录入人脸特征 / Get known faces from "features_all.csv"
def get_face_database(self):
if os.path.exists("data/features_all.csv"):
path_features_known_csv = "data/features_all.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
for i in range(csv_rd.shape[0]):
features_someone_arr = []
self.face_name_known_list.append(csv_rd.iloc[i][0])
for j in range(1, 129):
if csv_rd.iloc[i][j] == '':
features_someone_arr.append('0')
else:
features_someone_arr.append(csv_rd.iloc[i][j])
self.features_known_list.append(features_someone_arr)
logging.info("Faces in Database： %d", len(self.features_known_list))
return 1
else:
logging.warning("'features_all.csv' not found!")
logging.warning("Please run 'get_faces_from_camera.py' "
"and 'features_extraction_to_csv.py' before 'face_reco_from_camera.py'")
return 0
# 获取处理之后 stream 的帧数 / Update FPS of video stream
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
# 计算两个128D向量间的欧式距离 / Compute the e-distance between two 128D features
@staticmethod
def return_euclidean_distance(feature_1, feature_2):
feature_1 = np.array(feature_1)
feature_2 = np.array(feature_2)
dist = np.sqrt(np.sum(np.square(feature_1 - feature_2)))
return dist
# 生成的 cv2 window 上面添加说明文字 / putText on cv2 window
def draw_note(self, img_rd):
# 添加说明 (Add some statements
cv2.putText(img_rd, "Face Recognizer for single face", (20, 40), self.font, 1, (255, 255, 255), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Frame: " + str(self.frame_cnt), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps_show.__round__(2)), (20, 130), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(self.current_frame_face_cnt), (20, 160), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
def draw_name(self, img_rd):
# 在人脸框下面写人脸名字 / Write names under ROI
logging.debug(self.current_frame_name_list)
img = Image.fromarray(cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img)
draw.text(xy=self.current_frame_face_position_list[0], text=self.current_frame_name_list[0], font=self.font_chinese,
fill=(255, 255, 0))
img_rd = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
return img_rd
def show_chinese_name(self):
if self.current_frame_face_cnt >= 1:
logging.debug(self.face_name_known_list)
# 修改录入的人脸姓名 / Modify names in face_name_known_list to chinese name
self.face_name_known_list[0] = '张三'.encode('utf-8').decode()
# self.face_name_known_list[1] = '张四'.encode('utf-8').decode()
# 处理获取的视频流, 进行人脸识别 / Face detection and recognition wit OT from input video stream
def process(self, stream):
# 1. 读取存放所有人脸特征的 csv / Get faces known from "features.all.csv"
if self.get_face_database():
while stream.isOpened():
self.frame_cnt += 1
logging.debug("Frame " + str(self.frame_cnt) + " starts")
flag, img_rd = stream.read()
kk = cv2.waitKey(1)
# 2. 检测人脸 / Detect faces for frame X
faces = detector(img_rd, 0)
# 3. 更新帧中的人脸数 / Update cnt for faces in frames
self.last_frame_faces_cnt = self.current_frame_face_cnt
self.current_frame_face_cnt = len(faces)
# 4.1 当前帧和上一帧相比没有发生人脸数变化 / If cnt not changes, 1->1 or 0->0
if self.current_frame_face_cnt == self.last_frame_faces_cnt:
logging.debug("scene 1: 当前帧和上一帧相比没有发生人脸数变化 / No face cnt changes in this frame!!!")
if "unknown" in self.current_frame_name_list:
logging.debug(" >>> 有未知人脸, 开始进行 reclassify_interval_cnt 计数")
self.reclassify_interval_cnt += 1
# 4.1.1 当前帧一张人脸 / One face in this frame
if self.current_frame_face_cnt == 1:
if self.reclassify_interval_cnt == self.reclassify_interval:
logging.debug(" scene 1.1 需要对于当前帧重新进行人脸识别 / Re-classify for current frame")
self.reclassify_interval_cnt = 0
self.current_frame_face_feature_list = []
self.current_frame_face_X_e_distance_list = []
self.current_frame_name_list = []
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_face_feature_list.append(
face_reco_model.compute_face_descriptor(img_rd, shape))
# a. 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
self.current_frame_name_list.append("unknown")
# b. 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_face_position_list.append(tuple(
[faces[k].left(),
int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# c. 对于某张人脸, 遍历所有存储的人脸特征 / For every face detected, compare it with all the faces in the database
for i in range(len(self.features_known_list)):
# 如果 person_X 数据不为空 / If the data of person_X is not empty
if str(self.features_known_list[i][0]) != '0.0':
e_distance_tmp = self.return_euclidean_distance(
self.current_frame_face_feature_list[k],
self.features_known_list[i])
logging.debug(" with person %d, the e-distance: %f", i + 1, e_distance_tmp)
self.current_frame_face_X_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X / For empty data
self.current_frame_face_X_e_distance_list.append(999999999)
# d. 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
similar_person_num = self.current_frame_face_X_e_distance_list.index(
min(self.current_frame_face_X_e_distance_list))
if min(self.current_frame_face_X_e_distance_list) < 0.4:
# 在这里更改显示的人名 / Modify name if needed
self.show_chinese_name()
self.current_frame_name_list[k] = self.face_name_known_list[similar_person_num]
logging.debug(" recognition result for face %d: %s", k + 1,
self.face_name_known_list[similar_person_num])
else:
logging.debug(" recognition result for face %d: %s", k + 1, "unknown")
else:
logging.debug(
" scene 1.2 不需要对于当前帧重新进行人脸识别 / No re-classification needed for current frame")
# 获取特征框坐标 / Get ROI positions
for k, d in enumerate(faces):
cv2.rectangle(img_rd,
tuple([d.left(), d.top()]),
tuple([d.right(), d.bottom()]),
(255, 255, 255), 2)
self.current_frame_face_position_list[k] = tuple(
[faces[k].left(),
int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)])
img_rd = self.draw_name(img_rd)
# 4.2 当前帧和上一帧相比发生人脸数变化 / If face cnt changes, 1->0 or 0->1
else:
logging.debug("scene 2: 当前帧和上一帧相比人脸数发生变化 / Faces cnt changes in this frame")
self.current_frame_face_position_list = []
self.current_frame_face_X_e_distance_list = []
self.current_frame_face_feature_list = []
# 4.2.1 人脸数从 0->1 / Face cnt 0->1
if self.current_frame_face_cnt == 1:
logging.debug(" scene 2.1 出现人脸, 进行人脸识别 / Get faces in this frame and do face recognition")
self.current_frame_name_list = []
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_face_feature_list.append(
face_reco_model.compute_face_descriptor(img_rd, shape))
# a. 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
self.current_frame_name_list.append("unknown")
# b. 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_face_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# c. 对于某张人脸, 遍历所有存储的人脸特征 / For every face detected, compare it with all the faces in database
for i in range(len(self.features_known_list)):
# 如果 person_X 数据不为空 / If data of person_X is not empty
if str(self.features_known_list[i][0]) != '0.0':
e_distance_tmp = self.return_euclidean_distance(
self.current_frame_face_feature_list[k],
self.features_known_list[i])
logging.debug(" with person %d, the e-distance: %f", i + 1, e_distance_tmp)
self.current_frame_face_X_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X / Empty data for person_X
self.current_frame_face_X_e_distance_list.append(999999999)
# d. 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
similar_person_num = self.current_frame_face_X_e_distance_list.index(
min(self.current_frame_face_X_e_distance_list))
if min(self.current_frame_face_X_e_distance_list) < 0.4:
# 在这里更改显示的人名 / Modify name if needed
self.show_chinese_name()
self.current_frame_name_list[k] = self.face_name_known_list[similar_person_num]
logging.debug(" recognition result for face %d: %s", k + 1,
self.face_name_known_list[similar_person_num])
else:
logging.debug(" recognition result for face %d: %s", k + 1, "unknown")
if "unknown" in self.current_frame_name_list:
self.reclassify_interval_cnt += 1
# 4.2.1 人脸数从 1->0 / Face cnt 1->0
elif self.current_frame_face_cnt == 0:
logging.debug(" scene 2.2 人脸消失, 当前帧中没有人脸 / No face in this frame!!!")
self.reclassify_interval_cnt = 0
self.current_frame_name_list = []
self.current_frame_face_feature_list = []
# 5. 生成的窗口添加说明文字 / Add note on cv2 window
self.draw_note(img_rd)
if kk == ord('q'):
break
self.update_fps()
cv2.namedWindow("camera", 1)
cv2.imshow("camera", img_rd)
logging.debug("Frame ends\n\n")
def run(self):
# cap = cv2.VideoCapture("video.mp4") # Get video stream from video file
cap = cv2.VideoCapture(0) # Get video stream from camera
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
# logging.basicConfig(level=logging.DEBUG) # Set log level to 'logging.DEBUG' to print debug info of every frame
logging.basicConfig(level=logging.INFO)
Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run()
if __name__ == '__main__':
main()
对初始帧做检测+识别, 对后续帧做检测+质心跟踪（face_reco_from_camera_ot.py）：
class Face_Recognizer:
def __init__(self):
self.font = cv2.FONT_ITALIC
# FPS
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.fps_show = 0
self.start_time = time.time()
# cnt for frame
self.frame_cnt = 0
# 用来存放所有录入人脸特征的数组 / Save the features of faces in the database
self.face_features_known_list = []
# 存储录入人脸名字 / Save the name of faces in the database
self.face_name_known_list = []
# 用来存储上一帧和当前帧 ROI 的质心坐标 / List to save centroid positions of ROI in frame N-1 and N
self.last_frame_face_centroid_list = []
self.current_frame_face_centroid_list = []
# 用来存储上一帧和当前帧检测出目标的名字 / List to save names of objects in frame N-1 and N
self.last_frame_face_name_list = []
self.current_frame_face_name_list = []
# 上一帧和当前帧中人脸数的计数器 / cnt for faces in frame N-1 and N
self.last_frame_face_cnt = 0
self.current_frame_face_cnt = 0
# 用来存放进行识别时候对比的欧氏距离 / Save the e-distance for faceX when recognizing
self.current_frame_face_X_e_distance_list = []
# 存储当前摄像头中捕获到的所有人脸的坐标名字 / Save the positions and names of current faces captured
self.current_frame_face_position_list = []
# 存储当前摄像头中捕获到的人脸特征 / Save the features of people in current frame
self.current_frame_face_feature_list = []
# e distance between centroid of ROI in last and current frame
self.last_current_frame_centroid_e_distance = 0
# 控制再识别的后续帧数 / Reclassify after 'reclassify_interval' frames
# 如果识别出 "unknown" 的脸, 将在 reclassify_interval_cnt 计数到 reclassify_interval 后, 对于人脸进行重新识别
self.reclassify_interval_cnt = 0
self.reclassify_interval = 10
# 从 "features_all.csv" 读取录入人脸特征 / Get known faces from "features_all.csv"
def get_face_database(self):
if os.path.exists("data/features_all.csv"):
path_features_known_csv = "data/features_all.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
for i in range(csv_rd.shape[0]):
features_someone_arr = []
self.face_name_known_list.append(csv_rd.iloc[i][0])
for j in range(1, 129):
if csv_rd.iloc[i][j] == '':
features_someone_arr.append('0')
else:
features_someone_arr.append(csv_rd.iloc[i][j])
self.face_features_known_list.append(features_someone_arr)
logging.info("Faces in Database： %d", len(self.face_features_known_list))
return 1
else:
logging.warning("'features_all.csv' not found!")
logging.warning("Please run 'get_faces_from_camera.py' "
"and 'features_extraction_to_csv.py' before 'face_reco_from_camera.py'")
return 0
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
@staticmethod
# 计算两个128D向量间的欧式距离 / Compute the e-distance between two 128D features
def return_euclidean_distance(feature_1, feature_2):
feature_1 = np.array(feature_1)
feature_2 = np.array(feature_2)
dist = np.sqrt(np.sum(np.square(feature_1 - feature_2)))
return dist
# 使用质心追踪来识别人脸 / Use centroid tracker to link face_x in current frame with person_x in last frame
def centroid_tracker(self):
for i in range(len(self.current_frame_face_centroid_list)):
e_distance_current_frame_person_x_list = []
# 对于当前帧中的人脸1, 和上一帧中的 人脸1/2/3/4/.. 进行欧氏距离计算 / For object 1 in current_frame, compute e-distance with object 1/2/3/4/... in last frame
for j in range(len(self.last_frame_face_centroid_list)):
self.last_current_frame_centroid_e_distance = self.return_euclidean_distance(
self.current_frame_face_centroid_list[i], self.last_frame_face_centroid_list[j])
e_distance_current_frame_person_x_list.append(
self.last_current_frame_centroid_e_distance)
last_frame_num = e_distance_current_frame_person_x_list.index(
min(e_distance_current_frame_person_x_list))
self.current_frame_face_name_list[i] = self.last_frame_face_name_list[last_frame_num]
# 生成的 cv2 window 上面添加说明文字 / putText on cv2 window
def draw_note(self, img_rd):
# 添加说明 / Add some info on windows
cv2.putText(img_rd, "Face Recognizer with OT", (20, 40), self.font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Frame: " + str(self.frame_cnt), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps.__round__(2)), (20, 130), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(self.current_frame_face_cnt), (20, 160), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
for i in range(len(self.current_frame_face_name_list)):
img_rd = cv2.putText(img_rd, "Face_" + str(i + 1), tuple(
[int(self.current_frame_face_centroid_list[i][0]), int(self.current_frame_face_centroid_list[i][1])]),
self.font,
0.8, (255, 190, 0),
1,
cv2.LINE_AA)
# 处理获取的视频流, 进行人脸识别 / Face detection and recognition wit OT from input video stream
def process(self, stream):
# 1. 读取存放所有人脸特征的 csv / Get faces known from "features.all.csv"
if self.get_face_database():
while stream.isOpened():
self.frame_cnt += 1
logging.debug("Frame " + str(self.frame_cnt) + " starts")
flag, img_rd = stream.read()
kk = cv2.waitKey(1)
# 2. 检测人脸 / Detect faces for frame X
faces = detector(img_rd, 0)
# 3. 更新人脸计数器 / Update cnt for faces in frames
self.last_frame_face_cnt = self.current_frame_face_cnt
self.current_frame_face_cnt = len(faces)
# 4. 更新上一帧中的人脸列表 / Update the face name list in last frame
self.last_frame_face_name_list = self.current_frame_face_name_list[:]
# 5. 更新上一帧和当前帧的质心列表 / update frame centroid list
self.last_frame_face_centroid_list = self.current_frame_face_centroid_list
self.current_frame_face_centroid_list = []
# 6.1 如果当前帧和上一帧人脸数没有变化 / if cnt not changes
if (self.current_frame_face_cnt == self.last_frame_face_cnt) and (
self.reclassify_interval_cnt != self.reclassify_interval):
logging.debug("scene 1: 当前帧和上一帧相比没有发生人脸数变化 / No face cnt changes in this frame!!!")
self.current_frame_face_position_list = []
if "unknown" in self.current_frame_face_name_list:
logging.debug(" 有未知人脸, 开始进行 reclassify_interval_cnt 计数")
self.reclassify_interval_cnt += 1
if self.current_frame_face_cnt != 0:
for k, d in enumerate(faces):
self.current_frame_face_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
self.current_frame_face_centroid_list.append(
[int(faces[k].left() + faces[k].right()) / 2,
int(faces[k].top() + faces[k].bottom()) / 2])
img_rd = cv2.rectangle(img_rd,
tuple([d.left(), d.top()]),
tuple([d.right(), d.bottom()]),
(255, 255, 255), 2)
# 如果当前帧中有多个人脸, 使用质心追踪 / Multi-faces in current frame, use centroid-tracker to track
if self.current_frame_face_cnt != 1:
self.centroid_tracker()
for i in range(self.current_frame_face_cnt):
# 6.2 Write names under ROI
img_rd = cv2.putText(img_rd, self.current_frame_face_name_list[i],
self.current_frame_face_position_list[i], self.font, 0.8, (0, 255, 255), 1,
cv2.LINE_AA)
self.draw_note(img_rd)
# 6.2 如果当前帧和上一帧人脸数发生变化 / If cnt of faces changes, 0->1 or 1->0 or ...
else:
logging.debug("scene 2: 当前帧和上一帧相比人脸数发生变化 / Faces cnt changes in this frame")
self.current_frame_face_position_list = []
self.current_frame_face_X_e_distance_list = []
self.current_frame_face_feature_list = []
self.reclassify_interval_cnt = 0
# 6.2.1 人脸数减少 / Face cnt decreases: 1->0, 2->1, ...
if self.current_frame_face_cnt == 0:
logging.debug(" scene 2.1 人脸消失, 当前帧中没有人脸 / No faces in this frame!!!")
# clear list of names and features
self.current_frame_face_name_list = []
# 6.2.2 人脸数增加 / Face cnt increase: 0->1, 0->2, ..., 1->2, ...
else:
logging.debug(" scene 2.2 出现人脸, 进行人脸识别 / Get faces in this frame and do face recognition")
self.current_frame_face_name_list = []
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_face_feature_list.append(
face_reco_model.compute_face_descriptor(img_rd, shape))
self.current_frame_face_name_list.append("unknown")
# 6.2.2.1 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
logging.debug(" For face %d in current frame:", k + 1)
self.current_frame_face_centroid_list.append(
[int(faces[k].left() + faces[k].right()) / 2,
int(faces[k].top() + faces[k].bottom()) / 2])
self.current_frame_face_X_e_distance_list = []
# 6.2.2.2 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_face_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# 6.2.2.3 对于某张人脸, 遍历所有存储的人脸特征
# For every faces detected, compare the faces in the database
for i in range(len(self.face_features_known_list)):
# 如果 q 数据不为空
if str(self.face_features_known_list[i][0]) != '0.0':
e_distance_tmp = self.return_euclidean_distance(
self.current_frame_face_feature_list[k],
self.face_features_known_list[i])
logging.debug(" with person %d, the e-distance: %f", i + 1, e_distance_tmp)
self.current_frame_face_X_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
self.current_frame_face_X_e_distance_list.append(999999999)
# 6.2.2.4 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
similar_person_num = self.current_frame_face_X_e_distance_list.index(
min(self.current_frame_face_X_e_distance_list))
if min(self.current_frame_face_X_e_distance_list) < 0.4:
self.current_frame_face_name_list[k] = self.face_name_known_list[similar_person_num]
logging.debug(" Face recognition result: %s",
self.face_name_known_list[similar_person_num])
else:
logging.debug(" Face recognition result: Unknown person")
# 7. 生成的窗口添加说明文字 / Add note on cv2 window
self.draw_note(img_rd)
# cv2.imwrite("debug/debug_" + str(self.frame_cnt) + ".png", img_rd) # Dump current frame image if needed
# 8. 按下 'q' 键退出 / Press 'q' to exit
if kk == ord('q'):
break
self.update_fps()
cv2.namedWindow("camera", 1)
cv2.imshow("camera", img_rd)
logging.debug("Frame ends\n\n")
def run(self):
# cap = cv2.VideoCapture("video.mp4") # Get video stream from video file
cap = cv2.VideoCapture(0) # Get video stream from camera
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
# logging.basicConfig(level=logging.DEBUG) # Set log level to 'logging.DEBUG' to print debug info of every frame
logging.basicConfig(level=logging.INFO)
Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run()
if __name__ == '__main__':
main()
调用摄像头进行实时特征描述子计算（face_descriptor_from_camera.py）：
class Face_Descriptor:
def __init__(self):
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.frame_cnt = 0
def update_fps(self):
now = time.time()
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
def run(self):
cap = cv2.VideoCapture(0)
cap.set(3, 480)
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def process(self, stream):
while stream.isOpened():
flag, img_rd = stream.read()
self.frame_cnt+=1
k = cv2.waitKey(1)
print('- Frame ', self.frame_cnt, " starts:")
timestamp1 = time.time()
faces = detector(img_rd, 0)
timestamp2 = time.time()
print("--- Time used to `detector`: %s seconds ---" % (timestamp2 - timestamp1))
font = cv2.FONT_HERSHEY_SIMPLEX
# 检测到人脸
if len(faces) != 0:
for face in faces:
timestamp3 = time.time()
face_shape = predictor(img_rd, face)
timestamp4 = time.time()
print("--- Time used to `predictor`: %s seconds ---" % (timestamp4 - timestamp3))
timestamp5 = time.time()
face_desc = face_reco_model.compute_face_descriptor(img_rd, face_shape)
timestamp6 = time.time()
print("--- Time used to `compute_face_descriptor：` %s seconds ---" % (timestamp6 - timestamp5))
# 添加说明
cv2.putText(img_rd, "Face descriptor", (20, 40), font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps.__round__(2)), (20, 100), font, 0.8, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(len(faces)), (20, 140), font, 0.8, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(img_rd, "S: Save current face", (20, 400), font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
# 按下 'q' 键退出
if k == ord('q'):
break
self.update_fps()
cv2.namedWindow("camera", 1)
cv2.imshow("camera", img_rd)
print('\n')
def main():
Face_Descriptor_con = Face_Descriptor()
Face_Descriptor_con.run()
if __name__ == '__main__':
main()
至此模块化代码已经介绍完毕。
5、总结
本项目的核心是dlib机器学习库函数的运用，如果能熟练运用此库，就能掌握此项目。
-
如果希望详细了解 dlib 的用法, 请参考 Dlib 官方 Python api 的网站
-
代码最好不要有中文路径；
-
人脸录入的时候先建文件夹再保存图片, 先
N再S/ PressNbeforeS -
关于
face_reco_from_camera.py人脸识别卡顿 FPS 低问题, 原因是特征描述子提取很费时间; 光跑face_descriptor_from_camera.py中face_reco_model.compute_face_descriptor在我的机器上得到的平均 FPS 在 5 左右 (检测在0.03s, 特征描述子提取在0.158s, 和已知人脸进行遍历对比在0.003s左右); 所以主要提取特征时候耗资源, 可以用 OT 去做追踪 (使用face_reco_from_camera_ot.py), 而不是对每一帧都做检测+识别, 识别的性能从 20 FPS -> 200 FPS
文章出处登录后可见！
已经登录？立即刷新
