使用dlib实现人脸识别+活体检测

import face_recognition from imutils import face_utils from PIL import Image, ImageDraw,ImageFont import numpy as np import threading #导入threading模块 import yagmail import dlib import datetime import time import cv2 import os import sys # 初始化眨眼次数 blink_total = 0 # 初始化张嘴次数 mouth_total = 0 # 设置图片存储路径 # pic_path = './dataset' # 图片数量 pic_total = 0 # 初始化眨眼的连续帧数以及总的眨眼次数 blink_counter = 0 # 初始化张嘴状态为闭嘴 mouth_status_open = 0 # 眼长宽比例值 EAR_THRESH = 0.15 EAR_CONSEC_FRAMES_MIN = 1 EAR_CONSEC_FRAMES_MAX = 5 # 当EAR小于阈值时，接连多少帧一定发生眨眼动作 # 嘴长宽比例值 MAR_THRESH = 0.15 # 人脸检测器 detector = dlib.get_frontal_face_detector() # 特征点检测器 predictor = dlib.shape_predictor("modles/shape_predictor_68_face_landmarks.dat") # 获取左眼的特征点 (lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"] # 获取右眼的特征点 (rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"] # 获取嘴巴特征点 (mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["inner_mouth"] class Recorder: pass red_dict = {} unknownjpg = [] def sendemail(title,contents,fileslist):#将照片和访问记录上传云端 # yag = yagmail.SMTP("发件人邮箱",'密码' ,'smtp.qq.com', 465) # yag.send(['收件人邮箱1','收件人邮箱2'],title,contents,fileslist) yag=yagmail.SMTP("xxx@qq.com",'mbiwgdukvqaadfei','smtp.qq.com',465)#发件人邮箱 yag.send(['xxx@163.com','xxx@163.com'],title,contents,fileslist)#收件人邮箱(注意和上面邮箱不同) def dicttostr():#生成来访记录列表 strlist = [] listkey =list(sorted(red_dict.keys()))#取字典的key for item in listkey:#通过循环，合成每一条来访记录 strlist.extend([item + ','+str(onetime) for onetime in red_dict[item].times]) return strlist flagover = 0#全局标志，用来控制是否保持来访记录 def saveRecorder(name, frame):#保存和添加来访记录 global red_dict global flagover global unknownjpg if flagover == 1:#响应全局标志，如果为1时，关闭来访记录 return try: red = red_dict[name]#如果多次识别，比较时间 secondsDiff = (datetime.datetime.now() - red.times[-1]).total_seconds() if secondsDiff < 5*60: # 如果两次识别在5分钟内，将被过滤掉 return red.times.append(datetime.datetime.now()) print('更新记录', red_dict, red.times) except (KeyError): newRed = Recorder() newRed.times = [datetime.datetime.now()] red_dict[name] = newRed print('添加记录', red_dict, newRed.times) if name == 'Unknown': s = str(red_dict[name].times[-1]) print('写入', s[:10] + s[-6:]) filename = s[:10] + s[-6:] + '.jpg' cv2.imwrite(filename, frame) unknownjpg.append(filename) def loop_timer_headle(): # 定时器循环触发函数 print('————————Timer headle!————————', str(datetime.datetime.now())) global timer2 global flagover global red_dict global unknownjpg flagover = 1 timer2 = threading.Timer(60 * 5, loop_timer_headle) # 创建定时器 5分钟 timer2.start() # 发送邮件 sendemail("来访统计记录", '\n'.join(dicttostr()), unknownjpg) red_dict.clear() unknownjpg.clear() print("清空") time.sleep(10) print("重新开始") flagover = 0 timer2 = threading.Timer(2, loop_timer_headle) timer2.start() def load_img(sample_dir):#导入数据库照片 print('loading sample face..') for (dirpath, dirnames, filenames) in os.walk(sample_dir): # 一级一级的文件夹递归 print(dirpath, dirnames, filenames) facelib = [] for filename in filenames: filename_path = os.sep.join([dirpath, filename]) print(filename_path) faceimage = face_recognition.load_image_file(filename_path) # 由于我们每个图像只有一个脸，我只关心每个图像中的第一个编码，所以我取索引0 face_encoding = face_recognition.face_encodings(faceimage)[0] facelib.append(face_encoding) return facelib, filenames # def getFaceEncoding(src):#获取人脸编码 # image = face_recognition.load_image_file(src) # 加载人脸图片 # # 获取图片人脸定位[(top,right,bottom,left )] # face_locations = face_recognition.face_locations(image) # img_ = image[face_locations[0][0]:face_locations[0][2], face_locations[0][3]:face_locations[0][1]] # img_ = cv2.cvtColor(img_, cv2.COLOR_BGR2RGB) # # display(img_) # face_encoding = face_recognition.face_encodings(image, face_locations)[0] # 默认人脸数为1，对人脸图片进行编码 # return face_encoding #对比两张照片距离 # def simcos(a, b): # a = np.array(a) # b = np.array(b) # dist = np.linalg.norm(a - b) # 二范数 # sim = 1.0 / (1.0 + dist) # # return sim # 提供对外比对的接口 返回比对的相似度 # def comparison(face_src1, face_src2): # xl1 = getFaceEncoding(face_src1) # xl2 = getFaceEncoding(face_src2) # value = simcos(xl1, xl2) # print(value) # 眼长宽比例 def eye_aspect_ratio(eye): # (|e1-e5|+|e2-e4|) / (2|e0-e3|) A = np.linalg.norm(eye[1] - eye[5]) B = np.linalg.norm(eye[2] - eye[4]) C = np.linalg.norm(eye[0] - eye[3]) ear = (A + B) / (2.0 * C) return ear # 嘴长宽比例 def mouth_aspect_ratio(mouth): A = np.linalg.norm(mouth[1] - mouth[7]) # 61, 67 B = np.linalg.norm(mouth[3] - mouth[5]) # 63, 65 C = np.linalg.norm(mouth[0] - mouth[4]) # 60, 64 mar = (A + B) / (2.0 * C) return mar def main(): global blink_total # 使用global声明blink_total，在函数中就可以修改全局变量的值 global mouth_total global pic_total global blink_counter global mouth_status_open # video_path, src = sys.argv[1], sys.argv[2] facelib, facename = load_img('dataset') vs = cv2.VideoCapture(0) face_locations = [] # 定义列表存放人脸位置 face_encodings = [] # 定义列表存放人脸特征编码 process_this_frame = True # 定义信号量 while True: ret, frame = vs.read() # 捕获一帧图片 small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25) # 将图片缩小1/4，为人脸识别提速 rgb_small_frame = small_frame[:, :, ::-1] # 将opencv的BGR格式转为RGB格式 if process_this_frame: # 使用信号量对当前的处理进行保护 # 找到人脸位置，并生成特征码 face_locations = face_recognition.face_locations(rgb_small_frame) face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations) face_names = [] # 定义列表，放置识别结果 for face_encoding in face_encodings: # 循环多张人脸 matches = face_recognition.compare_faces(facelib, face_encoding) # 人脸识别 name = "Unknown" # 定义默认的识别结果为Unknown if True in matches: # 如果识别出来，就将名称取出 first_match_index = matches.index(True) name = facename[first_match_index][:-4] face_names.append(name) # 保存识别结果 process_this_frame = not process_this_frame # 信号量保护结束 # 显示结果 for (top, right, bottom, left), name in zip(face_locations, face_names): top *= 4 # 还原人脸的原始尺寸