一、相关文件下载及配置
- dlib 的配置 参考python3+opencv3.4+dlib库(人脸识别)
- shape_predictor_68_face_landmarks.dat和dlib_face_recognition_resnet_model_v1.dat
链接：https://pan.baidu.com/s/1r2ZesDtsfjQvk1gEqnxCyQ
提取码：0614
二、数据集的建立
1.录入图片
1.代码
get_from_camera.py
# 通过电脑摄像头实现对自己人脸的抓取，并储存在个人人脸数据库中，以备后面进行识别
import os
import shutil
import dlib # 人脸识别的库dlib
import numpy as np # 数据处理的库numpy
import cv2 # 图像处理的库OpenCv
# dlib预测器
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('./file/shape_predictor_68_face_landmarks.dat')
# 创建cv2摄像头对象
cap = cv2.VideoCapture(0)
# cap.set(propId, value)
# 设置视频参数，propId设置的视频参数，value设置的参数值
cap.set(3, 480)
# 截图screenshoot的计数器
cnt_ss = 0
# 人脸截图的计数器
cnt_p = 0
# 保存
path = "./dataset/faces/"
name = input('my name:')
# 如果路径存在则删除路径
path_save = os.path.join(path, name)
# 如果路径存在则删除路径
if os.path.isdir(path_save):
shutil.rmtree(path_save)
# 创建文件夹
os.mkdir(path_save)
# cap.isOpened（） 返回true/false 检查初始化是否成功
while cap.isOpened():
# cap.read()
# 返回两个值：
# 一个布尔值true/false，用来判断读取视频是否成功/是否到视频末尾
# 图像对象，图像的三维矩阵q
flag, im_rd = cap.read()
# 每帧数据延时1ms，延时为0读取的是静态帧
kk = cv2.waitKey(1)
# 取灰度
img_gray = cv2.cvtColor(im_rd, cv2.COLOR_RGB2GRAY)
# 人脸数rects
rects = detector(img_gray, 0)
# print(len(rects))
# 待会要写的字体
font = cv2.FONT_HERSHEY_SIMPLEX
if len(rects) != 0:
# 检测到人脸
# 矩形框
for k, d in enumerate(rects):
# 计算矩形大小
# (x,y), (宽度width, 高度height)
pos_start = tuple([d.left(), d.top()])
pos_end = tuple([d.right(), d.bottom()])
# 计算矩形框大小
height = d.bottom() - d.top()
width = d.right() - d.left()
# 根据人脸大小生成空的图像
cv2.rectangle(im_rd, tuple([d.left(), d.top()]), tuple([d.right(), d.bottom()]), (0, 255, 255), 2)
im_blank = np.zeros((height, width, 3), np.uint8)
# 按下's'保存摄像头中的人脸到本地
if kk == ord('s'):
cnt_p += 1
for ii in range(height):
for jj in range(width):
im_blank[ii][jj] = im_rd[d.top() + ii][d.left() + jj]
# 存储人脸图像文件
cv2.imwrite(path_save + "/img_face_" + str(cnt_p) + ".jpg", im_blank)
print("写入本地：", path_save + "/img_face_" + str(cnt_p) + ".jpg")
# 显示人脸数
cv2.putText(im_rd, "faces: " + str(len(rects)), (20, 50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
else:
# 没有检测到人脸
cv2.putText(im_rd, "no face", (20, 50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
# 添加说明
im_rd = cv2.putText(im_rd, "s: save face", (20, 400), font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
im_rd = cv2.putText(im_rd, "q: quit", (20, 450), font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
# 按下q键退出
if kk == ord('q'):
break
# 窗口显示
# cv2.namedWindow("camera", 0) # 如果需要摄像头窗口大小可调
cv2.imshow("camera", im_rd)
# 释放摄像头
cap.release()
# 删除建立的窗口
cv2.destroyAllWindows()
- 运行：
输入标识（姓名等），以此为文件名，将录入的图片保存至该目录下。
如以学号命名。
现在该目录下已经保存了我的20张图片。
2. 提取每张图片的特征值和特征均值
- 代码
get_features.py
# 从人脸图像文件中提取人脸特征存入 CSV
# Features extraction from images and save into features_all.csv
# return_128d_features() 获取某张图像的128D特征
# compute_the_mean() 计算128D特征均值
import cv2
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_images_from_camera = "./dataset/faces/"
# Dlib 正向人脸检测器
detector = dlib.get_frontal_face_detector()
# Dlib 人脸预测器
predictor = dlib.shape_predictor("./file/shape_predictor_68_face_landmarks.dat")
# Dlib 人脸识别模型
# Face recognition model, the object maps human faces into 128D vectors
face_rec = dlib.face_recognition_model_v1("./file/dlib_face_recognition_resnet_model_v1.dat")
# 返回单张图像的 128D 特征
def return_128d_features(path_img, exc=None):
img_rd = io.imread(path_img)
img_gray = cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB)
faces = detector(img_gray, 1)
print("%-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
if len(faces) != 0:
shape = predictor(img_gray, faces[0])
face_descriptor = face_rec.compute_face_descriptor(img_gray, shape)
# 将每张图片识别的特征值保存
# 全部保存至一个csv
# with open("./dataset/csvs/face_features.csv", "a", newline="") as cfile:
# 一张图一个csv
with open("./dataset/csvs/img_face_" + str(exc) + ".csv", "a", newline="") as cfile:
writer = csv.writer(cfile)
writer.writerow(face_descriptor)
print("特征值 / The features:", list(face_descriptor), '\n')
else:
face_descriptor = 0
print("no face", '\n')
return face_descriptor
# 将文件夹中照片特征提取出来, 写入 CSV
def return_features_mean_personX(path_faces_personX):
features_list_personX = []
exc=1
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
print("%-40s %-20s" % ("正在读的人脸图像 / image to read:", path_faces_personX + "/" + photos_list[i]))
features_128d = return_128d_features(path_faces_personX + "/" + photos_list[i],exc)
exc+=1
# print(features_128d)
# 遇到没有检测出人脸的图片跳过
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
# N x 128D -> 1 x 128D
if features_list_personX:
features_mean_personX = np.array(features_list_personX).mean(axis=0)
else:
features_mean_personX = '0'
return features_mean_personX
# 读取某人所有的人脸图像的数据
people = os.listdir(path_images_from_camera)
people.sort()
with open("./dataset/csvs/face_mean_features.csv", "w", newline="") as csvfile:
writer = csv.writer(csvfile)
for person in people:
print("##### " + person + " #####")
# Get the mean/average features of face/personX, it will be a list with a length of 128D
features_mean_personX = return_features_mean_personX(path_images_from_camera + person)
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: ./file/features_all2.csv")
- 结果
三、应用
- 代码
face_face.py
# 摄像头实时人脸识别
import os
import winsound # 系统音效
# from playsound import playsound # 音频播放
import dlib # 人脸处理的库 Dlib
import csv # 存入表格
import time
import sys
import numpy as np # 数据处理的库 numpy
import cv2 # 图像处理的库 OpenCv
import pandas as pd # 数据处理的库 Pandas
# 人脸识别模型，提取128D的特征矢量
# face recognition model, the object maps human faces into 128D vectors
# Refer this tutorial: http://dlib.net/python/index.html#dlib.face_recognition_model_v1
facerec = dlib.face_recognition_model_v1("./file/dlib_face_recognition_resnet_model_v1.dat")
# 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
# 处理存放所有人脸特征的 csv
path_features_known_csv = "./dataset/csvs/face_mean_features.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
# 用来存放所有录入人脸特征的数组
# the array to save the features of faces in the database
features_known_arr = []
# 读取已知人脸数据
# print known faces
for i in range(csv_rd.shape[0]):
features_someone_arr = []
for j in range(0, len(csv_rd.loc[i, :])):
features_someone_arr.append(csv_rd.loc[i, :][j])
features_known_arr.append(features_someone_arr)
print("Faces in Database：", len(features_known_arr))
# Dlib 检测器和预测器
# The detector and predictor will be used
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('./file/shape_predictor_68_face_landmarks.dat')
# 创建 cv2 摄像头对象
# cv2.VideoCapture(0) to use the default camera of PC,
# and you can use local video name by use cv2.VideoCapture(filename)
cap = cv2.VideoCapture(0)
# cap.set(propId, value)
# 设置视频参数，propId 设置的视频参数，value 设置的参数值
cap.set(3, 480)
# cap.isOpened() 返回 true/false 检查初始化是否成功
# when the camera is open
while cap.isOpened():
flag, img_rd = cap.read()
kk = cv2.waitKey(1)
# 取灰度
img_gray = cv2.cvtColor(img_rd, cv2.COLOR_RGB2GRAY)
# 人脸数 faces
faces = detector(img_gray, 0)
# 待会要写的字体 font to write later
font = cv2.FONT_HERSHEY_COMPLEX
# 存储当前摄像头中捕获到的所有人脸的坐标/名字
# the list to save the positions and names of current faces captured
pos_namelist = []
name_namelist = []
# 按下 q 键退出
# press 'q' to exit
if kk == ord('q'):
break
else:
# 检测到人脸 when face detected
if len(faces) != 0:
# 获取当前捕获到的图像的所有人脸的特征，存储到 features_cap_arr
# get the features captured and save into features_cap_arr
features_cap_arr = []
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
features_cap_arr.append(facerec.compute_face_descriptor(img_rd, shape))
# 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("##### camera person", k + 1, "#####")
# 让人名跟随在矩形框的下方
# 确定人名的位置坐标
# 先默认所有人不认识，是 unknown
# set the default names of faces with "unknown"
name_namelist.append("unknown")
# 每个捕获人脸的名字坐标 the positions of faces captured
pos_namelist.append(
tuple([faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# 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
e_distance_list = []
for i in range(len(features_known_arr)):
# 如果 person_X 数据不为空
if str(features_known_arr[i][0]) != '0.0':
print("with person", str(i + 1), "the e distance: ", end='')
e_distance_tmp = return_euclidean_distance(features_cap_arr[k], features_known_arr[i])
print(e_distance_tmp)
e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
e_distance_list.append(999999999)
# 找出最接近的一个人脸数据是第几个
# Find the one with minimum e distance
similar_person_num = e_distance_list.index(min(e_distance_list))
print("Minimum e distance with person", int(similar_person_num) + 1)
# 计算人脸识别特征与数据集特征的欧氏距离
# 距离小于0.4则标出为可识别人物
if min(e_distance_list) < 0.4:
# 这里可以修改摄像头中标出的人名
# Here you can modify the names shown on the camera
# 1、遍历文件夹目录
folder_name = './dataset/faces'
# 最接近的人脸
sum = similar_person_num + 1
key_id = 1 # 从第一个人脸数据文件夹进行对比
# 获取文件夹中的文件名:1wang、2zhou、3...
file_names = os.listdir(folder_name)
for name in file_names:
# print(name+'->'+str(key_id))
if sum == key_id:
# winsound.Beep(300,500)# 响铃：300频率，500持续时间
name_namelist[k] = name[:] # 人名删去第一个数字（用于视频输出标识）
key_id += 1
# 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)
print('\n')
# 在人脸框下面写人脸名字
# write names under rectangle
for i in range(len(faces)):
cv2.putText(img_rd, name_namelist[i], pos_namelist[i], font, 0.8, (0, 255, 255), 1, cv2.LINE_AA)
print("Faces in camera now:", name_namelist, "\n")
# cv2.putText(img_rd, "Press 'q': Quit", (20, 450), font, 0.8, (84, 255, 159), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Face Recognition", (20, 40), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Visitors: " + str(len(faces)), (20, 100), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
# 窗口显示 show with opencv
cv2.imshow("camera", img_rd)
# 释放摄像头 release camera
cap.release()
# 删除建立的窗口 delete all the windows
cv2.destroyAllWindows()
- 检测结果：
运行即可,不做演示。
扫一扫
2004
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
