使用opencv和face_recognition进行人脸识别_opencv 4.8 face recognition

该代码包含人脸数据采集和人脸识别两部分。

import face_recognition
import cv2 as cv
import numpy as np
import time
import os
class Rec_frg(object):
    #定义全局变量
    def __init__(self):
        self.video_path = r"D:\pythonItems\opencv1\vodeo"
        self.image_data_path = r"D:\pythonItems\opencv1\reg_facedata"
        self.nums = 40
        self.name = []
        self.face_encodings = []
    # 定义函数：用于计算视屏时长
    def video_duration(self,filename):
        cap = cv.VideoCapture(filename)
        if cap.isOpened():
            rate = cap.get(5)
            frame_num = cap.get(7)
            duration = frame_num // rate * 30
            times = duration // 60
            return times
        return -1

    #定义方法：用于收集数据
    def image_datacolloct(self):
        waitKey_count = 0
        #显示该文件夹下的所有内容
        video_path = os.listdir(self.video_path)
        #分别显示每一个视屏
        for path_v in video_path:
            img_num = 1
            # 找到每个视屏的绝对路径
            p = r"{}".format(os.path.join(self.video_path,path_v))
            #调用函数计算视屏时长
            all_times = self.video_duration(p)
            #打开视屏
            capture = cv.VideoCapture(p)
            while True:
                have_landmasks = True
                # 构造保存图片时图片的名称
                name = path_v.split(".")[0] +"_"+ str(img_num)
                # 通过视屏名称，找出每个人的名字
                label_name = path_v.split(".")[0]
                #显示时频每一帧
                ret, frame = capture.read()
                #缩小视屏宽、高为原来的一般
                frame = cv.resize(frame, (0, 0), fx=0.5, fy=0.5)
                #将每一帧的BGR格式转换为RGB格式
                rgb_small_frame_data = frame[:, :, ::-1]
                if ret == False:
                    break
                #找出每一帧中人脸的位置
                face_location = face_recognition.face_locations(rgb_small_frame_data)
                #训练集面部特征编码
                if waitKey_count == 0:
                    face_encoding = face_recognition.face_encodings(rgb_small_frame_data,model= "large")
                    if len(face_encoding) == 0:
                        have_landmasks = False
                    else:
                        have_landmasks = True
                        #将np.array()类型转换为list类型
                        fs = face_encoding[0].tolist()
                        #将数据和标签添加到列表中
                        self.face_encodings.append(fs)
                        self.name.append(label_name)
                        #保存图片
                        cv.imwrite("D:/pythonItems/opencv1/reg_facedata/"+name+".jpg",frame)
                        img_num += 1
                #设置退出条件
                if img_num > self.nums:
                    break
                c = cv.waitKey(1)
                if c == 27:
                    break
                #设置人脸数据获取条件
                if len(face_location) > 0 and have_landmasks == True:
                    waitKey_count += 1
                    print("wait",waitKey_count)
                if waitKey_count == all_times - 1:
                    waitKey_count = 0
                cv.imshow("face", frame)
            #释放资源
            capture.release()
        #显示收集好的数据及标签
        print("location", self.face_encodings)
        print("name", self.name)
        #将数据和标签存入文件中用于识别时使用
        f_data = open("data.txt", "w")
        f_name = open("name.txt","w")
        f_data.write(str(self.face_encodings))
        f_name.write(str(self.name))
        #关闭文件
        f_data.close()
        f_name.close()
        #关闭所有窗口
        cv.destroyAllWindows()
    #定义方法：用于识别
    def face_dances(self,video_name):
        success = 0
        fail = 0
        known_face_encodings = []
        video_capture = cv.VideoCapture(video_name)
        #读取人脸编码数据和标签
        data_file = open("data.txt", "r")
        label_file = open("name.txt","r")
        data = eval(data_file.read())
        #将从文件中读取出的每一张人脸数据的类型转化为 np.array()类型
        for i in data:
            list_to_array = np.array(i)
            known_face_encodings.append(list_to_array)
        known_face_names = eval(label_file.read())
        #关闭文件
        data_file.close()
        label_file.close()

        # 初始化变量
        process_this_frame = True
        time1 = time.time()

        while True:
            face_names = []
            name_str = ""
            # 读取视屏每一帧
            ret, frame = video_capture.read()
            if ret == False:
                break
            # 将视屏款、高缩小一半
            frame = cv.resize(frame, (0, 0), fx=0.5, fy=0.5)

            # 将BGR格式转化为RGB
            rgb_small_frame = frame[:, :, ::-1]

            # 只处理每隔一帧的视频以节省时间
            if process_this_frame:
                # 定位所找到的人脸的位置
                face_locations = face_recognition.face_locations(rgb_small_frame)
                # 对面部特征进行编码
                face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations,model= "large")
                #循环每一个编码好的人脸
                for face_encoding in face_encodings:
                    # 由面部编码匹配人脸
                    matches = face_recognition.compare_faces(known_face_encodings, face_encoding,tolerance=0.5)
                   #计算 "Ture" 的个数
                    true_count = matches.count(True)
                    # print(matches)
                    # print(true_count)
                    #计算要识别的人脸和每个已知人脸之间的距离
                    face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
                    #找出最小距离的索引
                    best_match_index = np.argmin(face_distances)
                    #判断条件
                    if matches[best_match_index] == False or true_count < self.nums:
                        name = "Unknown"
                        #循环每一张人脸
                        for top, right, bottom, left in face_locations:
                            #画出人脸框
                            cv.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
                            fail += 1
                            # 画出标签背景框
                            cv.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv.FILLED)
                            font = cv.FONT_HERSHEY_DUPLEX
                            #显示标签
                            cv.putText(frame, name, (left + 6, bottom - 6), font, 0.6, (255, 255, 255), 2)
                            if fail == 10:
                                print("识别失败！")
                                fail = 0
                                #计算时间
                                time2 = time.time()
                                spend = time2 - time1
                                print("花费时长：", spend)
                                time1 = time.time()

                    else:
                        #找出距离最小人脸的名字
                        name = known_face_names[best_match_index]
                        face_names.append(name)
                        #将人脸和相应的标签合并，并循环每一张人脸
                        for (top, right, bottom, left),name in zip(face_locations,face_names):
                            # 画出人脸框
                            cv.rectangle(frame, (left, top), (right, bottom), (0, 255, 0), 2)
                            success += 1
                            # 画出标签背景框
                            cv.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 255, 0), cv.FILLED)
                            font = cv.FONT_HERSHEY_DUPLEX
                            #显示标签
                            cv.putText(frame, name, (left + 6, bottom - 6), font, 0.6, (255, 255, 255), 2)
                            if success == 10:
                                for name_one in face_names:
                                    name_str += name_one+"  "
                                print("    识别成功！")
                                print(f"{name_str} 欢迎光临！")
                                time2 = time.time()
                                spend = time2 - time1
                                print("花费时长：", spend)
                                time1 = time.time()
                                success = 0


            # 显示每一帧视屏
            cv.imshow('Video', frame)

            #按ESC键退出
            key = cv.waitKey(1)
            if key == 27:
                break

        # 释放视屏资源，并关闭所有窗口
        video_capture.release()
        cv.destroyAllWindows()


#程序入口
if __name__ == "__main__":
    answer = input("人脸采集请输入0，输入其他进行识别！")
    video1 = "test.mp4"
    video2 = "girl_test.mp4"
    #实例化类
    Facerecognition = Rec_frg()
    #判断采集还是识别
    if answer == "0":
        Facerecognition.image_datacolloct()
        Facerecognition.face_dances(video1)
    else:
        Facerecognition.face_dances(video1)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225

结果(只显示人脸识别部分)：