本文章的所有代码和相关文章, 仅用于经验技术交流分享,禁止将相关技术应用到不正当途径,滥用技术产生的风险与本人无关。
本文章是自己学习的一些记录。
开始
最近这几天在帮老师整这个人脸识别的东西,前天我的室友“画画的baby”给了我一份资料就是匹配他的人脸,按照这个思路,我在网上找了很多的开源的资料,昨天找到了一个很好的开源的项目(准确率很高):
项目地址:
https://github.com/coneypo/Dlib_face_recognition_from_camera
项目步骤
该开源项目大致思路步骤:
主要是基于人脸识别库Dlib 的 ResNet 预训练模型,通过计算摄像头提取的人脸的特征值保存至.csv文件,然后利用dlib进行实时的人脸特征点的检测,主要提取人脸的128D特征,最后根据计算欧式距离,设定阈值处理,小于阈值的判定为该人,否则为未知的人脸。然后匹配出最为接近的一张人脸。
这个开源项目的大佬写的很好(膜拜)
这个大佬的博客地址:
https://www.cnblogs.com/AdaminXie/p/9010298.html
自己实现流程
1、先采集照片数据,存入数据库,为提取特征点做准备:
作者源码:get_faces_from_camera.py
# Copyright (C) 2020 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
# 进行人脸录入 / Face register
import dlib
import numpy as np
import cv2
import os
import shutil
import time
# Dlib 正向人脸检测器 / 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
# 新建保存人脸图像文件和数据CSV文件夹 / Make dir for saving photos and csv
def pre_work_mkdir(self):
# 新建文件夹 / Create folders to save faces 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 the old data of faces
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
# 获取处理之后 stream 的帧数 / Update FPS of video stream
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
# 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.__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)
print('\n')
print("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'):
print("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)
print("写入本地 / Save into:", str(current_face_dir) + "/img_face_" + str(self.ss_cnt) + ".jpg")
else:
print("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(0)
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
Face_Register_con = Face_Register()
Face_Register_con.run()
if __name__ == '__main__':
main()
视频窗口弹出来后,按住N创建一个文件夹,再按S进行截取人脸图像,按一下S保存一张,再按N就另外再创建一个文件夹,也就是第二个人的人脸图像存储位置,接着按S操作,进行保存。我一共采集了3个人的,分别为我的、梁朝伟的、梁博的。(我的是摄像头采集本人的,就不放了,怕吓着你们,梁朝伟和梁博是我用摄像头采集平板的照片采集的)
2、采集之后执行特征均值的存储,为.csv文件
作者源码:features_extraction_to_csv.py
# Copyright (C) 2020 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
# 从人脸图像文件中提取人脸特征存入 "features_all.csv" / Extract features from images and save into "features_all.csv"
import os
import dlib
from skimage import io
import csv
import numpy as np
# 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 = io.imread(path_img)
faces = detector(img_rd, 1)
print("%-40s %-20s" % ("检测到人脸的图像 / Image with faces detected:", path_img), '\n')
# 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
print("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_faces_personX <class 'str'>
# Output: features_mean_personX <class 'numpy.ndarray'>
def return_features_mean_personX(path_faces_personX):
features_list_personX = []
photos_list = os.listdir(path_faces_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
print("%-40s %-20s" % ("正在读的人脸图像 / Reading image:", path_faces_personX + "/" + photos_list[i]))
features_128d = return_128d_features(path_faces_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:
print("文件夹内图像文件为空 / Warning: No images in " + path_faces_personX + '/', '\n')
# 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).mean(axis=0)
else:
features_mean_personX = np.zeros(128, dtype=int, order='C')
print(type(features_mean_personX))
return features_mean_personX
# 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]))
person_cnt = max(person_num_list)
with open("data/features_all.csv", "w", newline="") as csvfile:
writer = csv.writer(csvfile)
for person in range(person_cnt):
# Get the mean/average features of face/personX, it will be a list with a length of 128D
print(path_images_from_camera + "person_" + str(person + 1))
features_mean_personX = return_features_mean_personX(path_images_from_camera + "person_" + str(person + 1))
writer.writerow(features_mean_personX)
print("特征均值 / The mean of features:", list(features_mean_personX))
print('\n')
print("所有录入人脸数据存入 / Save all the features of faces registered into: data/features_all.csv")
如果是原先有的.csv,作者的代码中可以重新生成剔除原先的.csv文件。
3、进行识别
作者源码:
# Copyright (C) 2020 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
# 摄像头实时人脸识别 / Real-time face detection and recognition
import dlib
import numpy as np
import cv2
import pandas as pd
import os
import time
from PIL import Image, ImageDraw, ImageFont
# 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")
class Face_Recognizer:
def __init__(self):
self.feature_known_list = [] # 用来存放所有录入人脸特征的数组 / Save the features of faces in the database
self.name_known_list = [] # 存储录入人脸名字 / Save the name of faces in the 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_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_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
self.current_frame_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
# Update FPS
self.fps = 0
self.frame_start_time = 0
# 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 = []
for j in range(0, 128):
if csv_rd.iloc[i][j] == '':
features_someone_arr.append('0')
else:
features_someone_arr.append(csv_rd.iloc[i][j])
self.feature_known_list.append(features_someone_arr)
self.name_known_list.append("Person_"+str(i+1))
print("Faces in Database:", len(self.feature_known_list))
return 1
else:
print('##### Warning #####', '\n')
print("'features_all.csv' not found!")
print(
"Please run 'get_faces_from_camera.py' and 'features_extraction_to_csv.py' before 'face_reco_from_camera.py'",
'\n')
print('##### End Warning #####')
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()
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
def draw_note(self, img_rd):
font = cv2.FONT_ITALIC
cv2.putText(img_rd, "Face Recognizer", (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(self.current_frame_face_cnt), (20, 140), font, 0.8, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), 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
font = ImageFont.truetype("simsun.ttc", 30)
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_name_list[i], self.current_frame_name_position_list[i], font, 0.8, (0, 255, 255), 1, cv2.LINE_AA)
draw.text(xy=self.current_frame_name_position_list[i], text=self.current_frame_name_list[i], font=font)
img_with_name = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
return img_with_name
# 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:
self.name_known_list[0] ='我'.encode('utf-8').decode()
self.name_known_list[1] ='梁朝伟'.encode('utf-8').decode()
self.name_known_list[2] ='梁博'.encode('utf-8').decode()
# self.name_known_list[3] ='xx'.encode('utf-8').decode()
# self.name_known_list[4] ='xx'.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 / Get faces known from "features.all.csv"
if self.get_face_database():
while stream.isOpened():
print(">>> Frame start")
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_feature_list = []
self.current_frame_face_cnt = 0
self.current_frame_name_position_list = []
self.current_frame_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_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)):
print(">>>>>> For face", k+1, " in camera")
# 先默认所有人不认识,是 unknown / Set the default names of faces with "unknown"
self.current_frame_name_list.append("unknown")
# 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_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.feature_known_list)):
# 如果 person_X 数据不为空
if str(self.feature_known_list[i][0]) != '0.0':
print(" >>> With person", str(i + 1), ", the e distance: ", end='')
e_distance_tmp = self.return_euclidean_distance(self.current_frame_feature_list[k],
self.feature_known_list[i])
print(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))
print(" >>> Minimum e distance with ", self.name_known_list[similar_person_num], ": ", min(current_frame_e_distance_list))
if min(current_frame_e_distance_list) < 0.4:
self.current_frame_name_list[k] = self.name_known_list[similar_person_num]
print(" >>> Face recognition result: " + str(self.name_known_list[similar_person_num]))
else:
print(" >>> Face recognition result: Unknown person")
# 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()]),
(0, 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
print(">>>>>> Faces in camera now:", self.current_frame_name_list)
cv2.imshow("camera", img_with_name)
# 9. 更新 FPS / Update stream FPS
self.update_fps()
print(">>> Frame ends\n\n")
# OpenCV 调用摄像头并进行 process
def run(self):
cap = cv2.VideoCapture(0)
# cap = cv2.VideoCapture("video.mp4")
cap.set(3, 480) # 640x480
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run()
if __name__ == '__main__':
main()
作者在这里self.show_chinese_name()原先是注释的,把这个放开了就可以在视频中显示中文了,就可以看见中文的名字了:
def show_chinese_name(self):
# Default known name: person_1, person_2, person_3
if self.current_frame_face_cnt >= 1:
self.name_known_list[0] ='我'.encode('utf-8').decode()
self.name_known_list[1] ='梁朝伟'.encode('utf-8').decode()
self.name_known_list[2] ='梁博'.encode('utf-8').decode()
# self.name_known_list[3] ='xx'.encode('utf-8').decode()
# self.name_known_list[4] ='xx'.encode('utf-8').decode()
在这里可以有几个人就可以加几个人的名字
识别效果还不错的
自己增加的内容
根据作者的识别的代码我主要加了两个内容:、
1、增加的识别后的语音播报:
使用的是pyttsx3这个库
在刷新帧率完成后进行播报识别的人名,多人可播报多人:
在self.update_fps()后面加的代码,还不算完美,但是每刷新一次都可以播报
text = '识别结果是' + str(self.current_frame_name_list)
voice = pyttsx3.init()
voice.say(text)
voice.runAndWait()
2、我自己用pyqt5写了一个人脸识别的图形应用界面:
还是得像开源作者多学习