def read_face():
# 读取 某人 所有的人脸图像的数据，写入 person_X.csv
faces = os.listdir(path_faces_rd)
for person in faces:
print(path_csv + person + ".csv")
write_into_csv(path_faces_rd + person, path_csv + person + ".csv")
# 存放所有特征均值的 CSV 的路径
path_csv_feature_all = getRoad() + "\\data\\features_all.csv"
# 存放人脸特征的csv的路径
path_csv_rd = getRoad() + "\\data\\csvs_from_camera\\"
with open(path_csv_feature_all, "w", newline="") as csvfile:
writer = csv.writer(csvfile)
csv_rd = os.listdir(path_csv_rd)
print("特征均值: ")
for i in range(len(csv_rd)):
feature_mean = compute_the_mean(path_csv_rd + csv_rd[i])
# print(feature_mean)
print(path_csv_rd + csv_rd[i])
writer.writerow(feature_mean)
def read_face():
# 读取 某人 所有的人脸图像的数据，写入 person_X.csv
faces = os.listdir(path_faces_rd)
for person in faces:
print(path_csv + person + ".csv")
write_into_csv(path_faces_rd + person, path_csv + person + ".csv")
# 存放人脸特征的csv的路径
path_csv_road = getRoad() + "\\data\\csvs_from_camera\\"
addFaceToDb = InertFaceFeatures()
csv_name = os.listdir(path_csv_road)
print("特征均值: ")
for i in range(len(csv_name)):
feature_mean = compute_the_mean(path_csv_road + csv_name[i])
feature_str = ','.join('%s' % id for id in feature_mean) # 列表转字符串
print(path_csv_road + csv_name[i])
# print(csv_name[i],feature_str)
addFaceToDb.insert(csv_name[i].replace('.csv', ''), feature_str)
# 摄像头实时人脸识别
# Real-time face recognition
import dlib # 人脸处理的库 Dlib
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
from util.ProjectRoad import getRoad
# 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(
getRoad() + "\\dlib\\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 = getRoad() + "\\data\\features_all.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
# return_128d_features() 获取某张图像的128d特征
# write_into_csv() 将某个文件夹中的图像读取特征并写入csv
# compute_the_mean() 从csv中读取128d特征，并计算特征均值
import csv
import os
import cv2
import dlib
import numpy as np
import pandas as pd
from skimage import io
from util.ProjectRoad import getRoad
path_faces_rd = getRoad() + "\\data\\faces_from_camera\\"
path_csv = getRoad() + "\\data\\csvs_from_camera\\"
# detector to find the faces 探测器
detector = dlib.get_frontal_face_detector()
# shape predictor to find the face landmarks 加载预测器
predictor = dlib.shape_predictor(
getRoad() + "\\dlib\\shape_predictor_5_face_landmarks.dat")
# face recognition model, the object maps human faces into 128D vectors 加载人脸识别模型
facerec = dlib.face_recognition_model_v1(
getRoad() + "\\dlib\\dlib_face_recognition_resnet_model_v1.dat")
# 返回单张图像的128D特征
def return_128d_features(path_img):
img = io.imread(path_img)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
import os
import shutil
import cv2 # 图像处理的库 OpenCv
# 进行人脸录入
# 录入多张人脸
import dlib # 人脸识别的库 Dlib
import numpy as np # 数据处理的库 Numpy
# Dlib 预测器
from util.GetInputBox import getInputGUI
from util.ProjectRoad import getRoad
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(
getRoad() + '\\dlib\\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
# 存储人脸的文件夹