目錄
一、準(zhǔn)備工作
1.1 需要的庫
1.2準(zhǔn)備需要的文件和圖片
1.3?測試程序
二、人臉識(shí)別開發(fā)
2.1 錄入自己的人臉信息
2.2 提取錄入的人臉特征
2.3 實(shí)時(shí)捕獲人臉并進(jìn)行識(shí)別
三、活體檢測
3.1 眨眼檢測
3.2 張嘴檢測
3.3 搖頭檢測
下面這些是我突發(fā)奇想想做來玩玩，就在github上下載了人臉識(shí)別的代碼（網(wǎng)址下面有附上），用了之后突然想試試照片的識(shí)別效果，發(fā)現(xiàn)照片也會(huì)被識(shí)別成我，就查閱了相關(guān)資料，一般都是通過活體檢測（比如眨眼、轉(zhuǎn)頭之類的），想通過算法實(shí)現(xiàn)實(shí)時(shí)視頻檢測，區(qū)分真人和照片。
一、準(zhǔn)備工作
開發(fā)環(huán)境：windows10+pycharm2022.1.3+python+3.9
1.1 需要的庫
opencv-python==4.5.5.64
numpy==1.23.3
dlib==19.24.0
pandas=1.5.0
枕頭=9.2.0
dlib庫安裝方法：
進(jìn)入虛擬環(huán)境后輸入：
anaconda search -t conda dlib
conda install -c https://conda.anaconda.org/conda-forge dlib
1.2準(zhǔn)備需要的文件和圖片
進(jìn)入網(wǎng)址：http://dlib.net/files/
下載文件：shape_predictor_68_face_landmarks.dat.bz2，解壓后存在data文件夾，該模型可以識(shí)別人臉68個(gè)關(guān)鍵點(diǎn)。網(wǎng)址中還含有5關(guān)鍵點(diǎn)模型文件。
準(zhǔn)備人臉照片，存于img文件夾。
1.3?測試程序
# -*- coding = utf-8 -*-
# @Time : 2022/9/20 9:11
# @Author : 李昊蕓
# @file : dlib_t.py
# @Software : PyCharm
import cv2
import dlib
path = "img/lhy_1.jpeg"
img = cv2.imread(path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#人臉分類器
detector = dlib.get_frontal_face_detector()
# 獲取人臉檢測器
predictor = dlib.shape_predictor(
".\\data\\shape_predictor_68_face_landmarks.dat"
)
dets = detector(gray, 1)
for face in dets:
shape = predictor(img, face) # 尋找人臉的68個(gè)標(biāo)定點(diǎn)
# 遍歷所有點(diǎn)，打印出其坐標(biāo)，并圈出來
for pt in shape.parts():
pt_pos = (pt.x, pt.y)
cv2.circle(img, pt_pos, 2, (0, 255, 0), 1)
cv2.imshow("image", img)
cv2.waitKey(0)
cv2.destroyAllWindows()68關(guān)鍵點(diǎn)分類器識(shí)別結(jié)果：
多人識(shí)別效果：
二、人臉識(shí)別開發(fā)
?原github地址：https://github.com/coneypo/Dlib_face_recognition_from_camera
2.1 錄入自己的人臉信息
get_faces_from_camera.py
# Copyright (C) 2018-2021 coneypo
# SPDX-License-Identifier: MIT
# Author: coneypo
# Blog: http://www.cnblogs.com/AdaminXie
# GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera
# Mail: coneypo@foxmail.com
# 進(jìn)行人臉錄入 / Face register
import dlib
import numpy as np
import cv2
import os
import shutil
import time
import logging
# Dlib 正向人臉檢測器 / Use frontal face detector of Dlib
detector = dlib.get_frontal_face_detector()
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 # 已錄入的人臉計(jì)數(shù)器 / cnt for counting saved faces
self.ss_cnt = 0 # 錄入 personX 人臉時(shí)圖片計(jì)數(shù)器 / cnt for screen shots
self.current_frame_faces_cnt = 0 # 錄入人臉計(jì)數(shù)器 / cnt for counting faces in current frame
self.save_flag = 1 # 之后用來控制是否保存圖像的 flag / The flag to control if save
self.press_n_flag = 0 # 之后用來檢查是否先按 '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()
# 新建保存人臉圖像文件和數(shù)據(jù) CSV 文件夾 / Mkdir for saving photos and csv
def pre_work_mkdir(self):
# 新建文件夾 / 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)
# 刪除之前存的人臉數(shù)據(jù)文件夾 / Delete old face folders
def pre_work_del_old_face_folders(self):
# 刪除之前存的人臉數(shù)據(jù)文件夾, 刪除 "/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")
# 如果有之前錄入的人臉, 在之前 person_x 的序號(hào)按照 person_x+1 開始錄入 / Start from person_x+1
def check_existing_faces_cnt(self):
if os.listdir("data/data_faces_from_camera/"):
# 獲取已錄入的最后一個(gè)人臉序號(hào) / 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)
# 如果第一次存儲(chǔ)或者沒有之前錄入的人臉, 按照 person_1 開始錄入 / 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 上面添加說明文字 / PutText on cv2 window
def draw_note(self, img_rd):
# 添加說明 / 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)
# 獲取人臉 / Main process of face detection and saving
def process(self, stream):
# 1. 新建儲(chǔ)存人臉圖像文件目錄 / Create folders to save photos
self.pre_work_mkdir()
# 2. 刪除 "/data/data_faces_from_camera" 中已有人臉圖像文件
# / 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. 檢查 "/data/data_faces_from_camera" 中已有人臉文件
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' 新建存儲(chǔ)人臉的文件夾 / 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", "新建的人臉文件夾 / Create folders:", current_face_dir)
self.ss_cnt = 0 # 將人臉計(jì)數(shù)器清零 / Clear the cnt of screen shots
self.press_n_flag = 1 # 已經(jīng)按下 'n' / Pressed 'n' already
# 5. 檢測到人臉 / Face detected
if len(faces) != 0:
# 矩形框 / Show the ROI of faces
for k, d in enumerate(faces):
# 計(jì)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. 判斷人臉矩形框是否超出 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("請調(diào)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. 根據(jù)人臉大小生成空的圖像 / 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' 保存攝像頭中的人臉到本地 / Press 's' to save faces into local images
if kk == ord('s'):
# 檢查有沒有先按'n'新建文件夾 / 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", "寫入本地 / Save into：",
str(current_face_dir), str(self.ss_cnt))
else:
logging.warning("請先按 'N' 來建文件夾, 按 'S' / Please press 'N' and press 'S'")
self.current_frame_faces_cnt = len(faces)
# 9. 生成的窗口添加說明文字 / Add note on cv2 window
self.draw_note(img_rd)
# 10. 按下 'q' 鍵退出 / 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()2.2 提取錄入的人臉特征
features_extraction_to_csv.py
# Copyright (C) 2018-2021 coneypo
# SPDX-License-Identifier: MIT
# Author: coneypo
# Blog: http://www.cnblogs.com/AdaminXie
# GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera
# Mail: coneypo@foxmail.com
# 從人臉圖像文件中提取人臉特征存入 "features_all.csv" / Extract features from images and save into "features_all.csv"
import os
import dlib
import csv
import numpy as np
import logging
import cv2
# 要讀取人臉圖像文件的路徑 / Path of cropped faces
path_images_from_camera = "data/data_faces_from_camera/"
# Dlib 正向人臉檢測器 / Use frontal face detector of Dlib
detector = dlib.get_frontal_face_detector()
# Dlib 人臉 landmark 特征點(diǎn)檢測器 / Get face landmarks
predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat')
# Dlib Resnet 人臉識(shí)別模型，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")
# 返回單張圖像的 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", "檢測到人臉的圖像 / Image with faces detected:", path_img)
# 因?yàn)橛锌赡芙叵聛淼娜四樤偃z測，檢測不出來人臉了, 所以要確保是 檢測到人臉的人臉圖像拿去算特征
# 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)):
# 調(diào)用 return_128d_features() 得到 128D 特征 / Get 128D features for single image of personX
logging.info("%-40s %-20s", "正在讀的人臉圖像 / Reading image:", path_face_personX + "/" + photos_list[i])
features_128d = return_128d_features(path_face_personX + "/" + photos_list[i])
# 遇到?jīng)]有檢測出人臉的圖片跳過 / Jump if no face detected from image
if features_128d == 0:
i += 1
else:
features_list_personX.append(features_128d)
else:
logging.warning("文件夾內(nèi)圖像文件為空 / Warning: No images in%s/", path_face_personX)
# 計(jì)算 128D 特征的均值 / Compute the mean
# personX 的 N 張圖像 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)
# 獲取已錄入的最后一個(gè)人臉序號(hào) / 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("所有錄入人臉數(shù)據(jù)存入 / Save all the features of faces registered into: data/features_all.csv")
if __name__ == '__main__':
main()2.3 實(shí)時(shí)捕獲人臉并進(jìn)行識(shí)別
face_reco_from_camera.py
# Copyright (C) 2018-2021 coneypo
# SPDX-License-Identifier: MIT
# Author: coneypo
# Blog: http://www.cnblogs.com/AdaminXie
# GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera
# Mail: coneypo@foxmail.com
# 攝像頭實(shí)時(shí)人臉識(shí)別 / Real-time face detection and recognition
import dlib
import numpy as np
import cv2
import pandas as pd
import os
import time
import logging
from PIL import Image, ImageDraw, ImageFont
# Dlib 正向人臉檢測器 / Use frontal face detector of Dlib
detector = dlib.get_frontal_face_detector()
# Dlib 人臉 landmark 特征點(diǎn)檢測器 / Get face landmarks
predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat')
# Dlib Resnet 人臉識(shí)別模型，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")
class Face_Recognizer:
def __init__(self):
self.face_feature_known_list = [] # 用來存放所有錄入人臉特征的數(shù)組 / Save the features of faces in database
self.face_name_known_list = [] # 存儲(chǔ)錄入人臉名字 / Save the name of faces in database
self.current_frame_face_cnt = 0 # 存儲(chǔ)當(dāng)前攝像頭中捕獲到的人臉數(shù) / Counter for faces in current frame
self.current_frame_face_feature_list = [] # 存儲(chǔ)當(dāng)前攝像頭中捕獲到的人臉特征 / Features of faces in current frame
self.current_frame_face_name_list = [] # 存儲(chǔ)當(dāng)前攝像頭中捕獲到的所有人臉的名字 / Names of faces in current frame
self.current_frame_face_name_position_list = [] # 存儲(chǔ)當(dāng)前攝像頭中捕獲到的所有人臉的名字坐標(biāo) / 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)
# 從 "features_all.csv" 讀取錄入人臉特征 / 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
# 計(jì)算兩個(gè)128D向量間的歐式距離 / 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 上面添加說明文字 / 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):
# 在人臉框下面寫人臉名字 / 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
# 修改顯示人名 / 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:
# 修改錄入的人臉姓名 / Modify names in face_name_known_list to chinese name
self.face_name_known_list[0] = '張三'.encode('utf-8').decode()
# self.face_name_known_list[1] = '張四'.encode('utf-8').decode()
# 處理獲取的視頻流，進(jìn)行人臉識(shí)別 / Face detection and recognition from input video stream
def process(self, stream):
# 1. 讀取存放所有人臉特征的 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 鍵退出 / 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. 檢測到人臉 / Face detected in current frame
if len(faces) != 0:
# 3. 獲取當(dāng)前捕獲到的圖像的所有人臉的特征 / 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. 遍歷捕獲到的圖像中所有的人臉 / Traversal all the faces in the database
for k in range(len(faces)):
logging.debug("For face %d in camera:", k+1)
# 先默認(rèn)所有人不認(rèn)識(shí)，是 unknown / Set the default names of faces with "unknown"
self.current_frame_face_name_list.append("unknown")
# 每個(gè)捕獲人臉的名字坐標(biāo) / 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. 對于某張人臉，遍歷所有存儲(chǔ)的人臉特征
# 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 數(shù)據(jù)不為空
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:
# 空數(shù)據(jù) person_X
current_frame_e_distance_list.append(999999999)
# 6. 尋找出最小的歐式距離匹配 / 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):
# 繪制矩形框
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. 在這里更改顯示的人名 / Modify name if needed
# self.show_chinese_name()
# 8. 寫名字 / 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 調(diào)用攝像頭并進(jìn)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()
識(shí)別結(jié)果（我和我的無美顏照片）：
（自己的臉，馬賽克一下）?
可以看出， 識(shí)別效果還是很不錯(cuò)的。
三、活體檢測
3.1 眨眼檢測
經(jīng)過查詢資料，得到廣為人使用的一個(gè)指標(biāo)：眼睛縱橫比（EAR）
分別得到兩只眼睛的縱橫比并取平均值，作為眨眼的指標(biāo)，經(jīng)過多次測試后，選取0.3作為閾值。
在連續(xù)檢測到兩次EAR小于閾值，即眼睛一睜一閉時(shí)，我們將記錄為一次眨眼。
代碼如下，實(shí)驗(yàn)結(jié)果如圖：
from scipy.spatial import distance as dist
from imutils.video import VideoStream
from imutils import face_utils
import imutils
import time
import dlib
import cv2
def EAR(eye):
# 計(jì)算眼睛的兩組垂直關(guān)鍵點(diǎn)之間的歐式距離
A = dist.euclidean(eye[1], eye[5]) # 1,5是一組垂直關(guān)鍵點(diǎn)
B = dist.euclidean(eye[2], eye[4]) # 2,4是一組
# 計(jì)算眼睛的一組水平關(guān)鍵點(diǎn)之間的歐式距離
C = dist.euclidean(eye[0], eye[3]) # 0,3是一組水平關(guān)鍵點(diǎn)
return (A + B) / (2.0 * C)
def main():
EAR_THRESH = 0.3 # 眨眼閾值
EYE_close = 2 # 閉眼次數(shù)閾值
# 初始化眨眼幀計(jì)數(shù)器和總眨眼次數(shù)
count_eye = 0
total = 0
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
# 左右眼的索引
(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]
(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]
vs = VideoStream(src=0).start()
time.sleep(1.0)
while True:
frame = vs.read()
frame = imutils.resize(frame, width=600)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 在灰度框中檢測人臉
rects = detector(gray, 0)
# 進(jìn)入循環(huán)
for rect in rects:
shape = predictor(gray, rect)
shape = face_utils.shape_to_np(shape)
# 提取左眼和右眼坐標(biāo)，然后使用該坐標(biāo)計(jì)算兩只眼睛的眼睛縱橫比
leftEye = shape[lStart:lEnd]
rightEye = shape[rStart:rEnd]
ear = EAR(leftEye) + EAR(rightEye) / 2.0
# 判斷眼睛縱橫比是否低于眨眼閾值
if ear < EAR_THRESH:
count_eye += 1
else:
# 檢測到一次閉眼
if count_eye >= EYE_close:
total += 1
count_eye = 0
# 畫出畫框上眨眼的總次數(shù)以及計(jì)算出的幀的眼睛縱橫比
cv2.putText(frame, "Blinks: {}".format(total), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
cv2.destroyAllWindows()
vs.stop()
if __name__ == '__main__':
main()
3.2 張嘴檢測
同理，可以做張嘴檢測：
from imutils.video import VideoStream
from imutils import face_utils
import imutils
import time
import dlib
import cv2
import numpy as np
def MAR(mouth):
# 默認(rèn)二范數(shù)：求特征值，然后求最大特征值得算術(shù)平方根
A = np.linalg.norm(mouth[2] - mouth[9]) # 51, 59（人臉68個(gè)關(guān)鍵點(diǎn)）
B = np.linalg.norm(mouth[4] - mouth[7]) # 53, 57
C = np.linalg.norm(mouth[0] - mouth[6]) # 49, 55
return (A + B) / (2.0 * C)
def main():
MAR_THRESH = 0.5 # 張嘴閾值
# 初始化
COUNTER_MOUTH = 0
TOTAL_MOUTH = 0
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
# 嘴的索引
(mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["mouth"]
vs = VideoStream(src=0).start()
time.sleep(1.0)
while True:
frame = vs.read()
frame = imutils.resize(frame, width=600)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 在灰度框中檢測人臉
rects = detector(gray, 0)
# 進(jìn)入循環(huán)
for rect in rects:
shape = predictor(gray, rect)
shape = face_utils.shape_to_np(shape)
# 提取嘴唇坐標(biāo)，然后使用該坐標(biāo)計(jì)算嘴唇縱橫比
Mouth = shape[mStart:mEnd]
mar = MAR(Mouth)
# 判斷嘴唇縱橫比是否高于張嘴閾值，如果是，則增加張嘴幀計(jì)數(shù)器
if mar > MAR_THRESH:
COUNTER_MOUTH += 1
else:
# 如果張嘴幀計(jì)數(shù)器不等于0，則增加張嘴的總次數(shù)
if COUNTER_MOUTH >= 2:
TOTAL_MOUTH += 1
COUNTER_MOUTH = 0
cv2.putText(frame, "Mouth is open: {}".format(TOTAL_MOUTH), (10, 60),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.putText(frame, "MAR: {:.2f}".format(mar), (300, 60),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
cv2.destroyAllWindows()
vs.stop()
if __name__ == '__main__':
main()3.3 搖頭檢測
在手機(jī)很多App如支付寶中，搖頭也屬于非常常見的活體檢測手段，此項(xiàng)采用鼻子到左右臉的歐氏距離變化，判斷是否搖頭。
文章來源：http://www.zghlxwxcb.cn/news/detail-401870.html
代碼如下：文章來源地址http://www.zghlxwxcb.cn/news/detail-401870.html
from scipy.spatial import distance as dist
from imutils.video import VideoStream
from imutils import face_utils
import imutils
import time
import dlib
import cv2
def nose_jaw_distance(nose, jaw):
# 計(jì)算鼻子上一點(diǎn)"27"到左右臉邊界的歐式距離
face_left1 = dist.euclidean(nose[0], jaw[0]) # 27, 0
face_right1 = dist.euclidean(nose[0], jaw[16]) # 27, 16
# 計(jì)算鼻子上一點(diǎn)"30"到左右臉邊界的歐式距離
face_left2 = dist.euclidean(nose[3], jaw[2]) # 30, 2
face_right2 = dist.euclidean(nose[3], jaw[14]) # 30, 14
# 創(chuàng)建元組，用以保存4個(gè)歐式距離值
face_distance = (face_left1, face_right1, face_left2, face_right2)
return face_distance
def main():
# 初始化眨眼幀計(jì)數(shù)器和總眨眼次數(shù)
distance_left = 0
distance_right = 0
TOTAL_FACE = 0
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
(nStart, nEnd) = face_utils.FACIAL_LANDMARKS_IDXS["nose"]
(jStart, jEnd) = face_utils.FACIAL_LANDMARKS_IDXS['jaw']
vs = VideoStream(src=0).start()
time.sleep(1.0)
while True:
frame = vs.read()
frame = imutils.resize(frame, width=600)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 在灰度框中檢測人臉
rects = detector(gray, 0)
# 進(jìn)入循環(huán)
for rect in rects:
shape = predictor(gray, rect)
shape = face_utils.shape_to_np(shape)
# 提取鼻子和下巴的坐標(biāo)，然后使用該坐標(biāo)計(jì)算鼻子到左右臉邊界的歐式距離
nose = shape[nStart:nEnd]
jaw = shape[jStart:jEnd]
NOSE_JAW_Distance = nose_jaw_distance(nose, jaw)
# 移植鼻子到左右臉邊界的歐式距離
face_left1 = NOSE_JAW_Distance[0]
face_right1 = NOSE_JAW_Distance[1]
face_left2 = NOSE_JAW_Distance[2]
face_right2 = NOSE_JAW_Distance[3]
# 根據(jù)鼻子到左右臉邊界的歐式距離，判斷是否搖頭
# 左臉大于右臉
if face_left1 >= face_right1 + 2 and face_left2 >= face_right2 + 2:
distance_left += 1
# 右臉大于左臉
if face_right1 >= face_left1 + 2 and face_right2 >= face_left2 + 2:
distance_right += 1
# 左臉大于右臉，并且右臉大于左臉，判定搖頭
if distance_left != 0 and distance_right != 0:
TOTAL_FACE += 1
distance_right = 0
distance_left = 0
# 畫出搖頭次數(shù)
cv2.putText(frame, "shake one's head: {}".format(TOTAL_FACE), (10, 90),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
cv2.destroyAllWindows()
vs.stop()
if __name__ == '__main__':
main()到了這里，關(guān)于通過Dlib和opencv實(shí)現(xiàn)人臉識(shí)別和活體檢測的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
