Dlib模型实现人脸识别
一、安装dlib库下载Dlib安装包下载链接:http://dlib.net/files/本文章下载的是dlib-19.14.zip,下载完成后解压安装dlib安装Cmake下载链接:https://cmake.org/download/下载安装包直接点击安装就行,注意环境变量的设置下载boost下载链接:http://www.boost.org/下载之后将其解压缩,进入解压后的文件夹中,找到bo
·
环境说明:
python3.6+spyder
第三方库的说明
skimage,playsound
安装命令:
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple scikit-image
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple playsound
一、安装dlib库
- 下载Dlib安装包
下载链接:http://dlib.net/files/
本文章下载的是dlib-19.14.zip
,下载完成后解压安装dlib - 安装Cmake
下载链接:https://cmake.org/download/
下载安装包直接点击安装就行,注意环境变量的设置 - 下载boost
下载链接:http://www.boost.org/
下载之后将其解压缩,进入解压后的文件夹中,找到bootstrap.bat批处理文件,双击运行,等待运行完成后(命令行自动消失)会生成文件b2.exe
win+R,打开命令行,进入b2.exe所在的文件夹,运行下面命令
b2编译库文件b2 install
安装完成后配置boost环境变量b2 -a -python address-model=64 toolset=msvc runtime-link=static #cmake下载的64位这里(address-model)写64,如果是32位的就把之前的64改成32
- 安装dlib
命令行进入dlib的文件夹中
安装完成后,在文件夹下面会出现dlib,dlib.egg-info,dist的三个文件夹python setup.py install
将dlib 和dlib.egg-info 复制对应python环境下的Lib文件,同时将build\lib.win-amd64-3.6文件夹下的dlib.cp36-win_amd64.pyd复制到对应python环境下的DLL文件夹
测试是否安装成功(没有报错,表示安装成功)
二、利用dlib实现人脸68个关键点检测并标注
- 下载官方的训练模型
下载链接:
http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2 - 人脸检测和标注
标注结果import numpy as np import cv2 import dlib #detector = dlib.get_frontal_face_detector() detector=dlib.get_frontal_face_detector() predictor = dlib.shape_predictor('E:\\PersonRecognitionDlib\\shape_predictor_68_face_landmarks.dat\\shape_predictor_68_face_landmarks.dat') # cv2读取图像 img = cv2.imread("E:\\PersonRecognitionDlib\\text.jpg") #print(img) # 取灰度 img_gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) # 人脸数rects rects = detector(img_gray, 1) for i in range(len(rects)): landmarks = np.matrix([[p.x, p.y] for p in predictor(img,rects[i]).parts()]) for idx, point in enumerate(landmarks): # 68点的坐标 pos = (point[0, 0], point[0, 1]) print(idx,pos) # 利用cv2.circle给每个特征点画一个圈,共68个 cv2.circle(img, pos, 5, color=(0, 255, 0)) # 利用cv2.putText输出1-68 font = cv2.FONT_HERSHEY_SIMPLEX cv2.putText(img, str(idx+1), pos, font, 0.8, (0, 0, 255), 1,cv2.LINE_AA) cv2.namedWindow("img", 2) cv2.imshow("img", img) cv2.waitKey(0)
问题描述:module 'dlib' has no attribute 'get_frontal_face_detector'
解决方法:将python环境更换为3.6
三、人脸特征提取
- 人脸数据集
①使用摄像头采集(视频流截图)
采集的过程,最好使用同一设备同一光线下进行采集import cv2 import dlib import os import sys import random # 存储位置 output_dir = 'D:/myworkspace/JupyterNotebook/People/person/person1' size = 64 if not os.path.exists(output_dir): os.makedirs(output_dir) # 改变图片的亮度与对比度 def relight(img, light=1, bias=0): w = img.shape[1] h = img.shape[0] #image = [] for i in range(0,w): for j in range(0,h): for c in range(3): tmp = int(img[j,i,c]*light + bias) if tmp > 255: tmp = 255 elif tmp < 0: tmp = 0 img[j,i,c] = tmp return img #使用dlib自带的frontal_face_detector作为我们的特征提取器 detector = dlib.get_frontal_face_detector() # 打开摄像头 参数为输入流,可以为摄像头或视频文件 camera = cv2.VideoCapture(0) index = 1 while True: if (index <= 15):#存储15张人脸特征图像 print('Being processed picture %s' % index) # 从摄像头读取照片 success, img = camera.read() # 转为灰度图片 gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 使用detector进行人脸检测 dets = detector(gray_img, 1) for i, d in enumerate(dets): x1 = d.top() if d.top() > 0 else 0 y1 = d.bottom() if d.bottom() > 0 else 0 x2 = d.left() if d.left() > 0 else 0 y2 = d.right() if d.right() > 0 else 0 face = img[x1:y1,x2:y2] # 调整图片的对比度与亮度, 对比度与亮度值都取随机数,这样能增加样本的多样性 face = relight(face, random.uniform(0.5, 1.5), random.randint(-50, 50)) face = cv2.resize(face, (size,size)) cv2.imshow('image', face) cv2.imwrite(output_dir+'/'+str(index)+'.jpg', face) index += 1 key = cv2.waitKey(30) & 0xff if key == 27: break else: print('Finished!') # 释放摄像头 release camera camera.release() # 删除建立的窗口 delete all the windows cv2.destroyAllWindows() break
在对应的输出目录下,会得到15张摄像头采集得到的图片。
②网络爬虫获取
具体内容可以参考链接:
https://blog.csdn.net/cungudafa/article/details/87862687 - 数据集的处理
- 获取特征点
①下载dlib的人脸识别模型
下载链接:
https://pan.baidu.com/s/1sBH4TvIfIYLFYs7zCTH4nA
提取码:b8zu
②获取每个人68个特征数据并保存到csv中from cv2 import cv2 as 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 = "E:/PersonRecognitionDlib/Person/" # Dlib 正向人脸检测器 detector = dlib.get_frontal_face_detector() # Dlib 人脸预测器 predictor = dlib.shape_predictor("E:/PersonRecognitionDlib/model/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("E:/PersonRecognitionDlib/model/dlib_face_recognition_resnet_model_v1.dat") # 返回单张图像的 128D 特征 def return_128d_features(path_img): 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), '\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 if len(faces) != 0: shape = predictor(img_gray, faces[0]) face_descriptor = face_rec.compute_face_descriptor(img_gray, shape) else: face_descriptor = 0 print("no face") 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 = [] 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]) # 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("E:/PersonRecognitionDlib/feature/features2_all.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: D:/myworkspace/JupyterNotebook/People/feature/features_all2.csv")
四、人脸识别
- 计算距离——欧氏距离
将要识别的对象与已经存在的对象进行距离计算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
- 实现人脸识别
整个过程是先进行人脸的检测,检测摄像头所采集到的人脸,然后将检测到的人脸对象与数据集中的人脸68个特征点进行一个距离计算,然后,选出最接近的那个人,接着判断距离小于0.4,就可以标识出识别人物。# 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 from cv2 import cv2 as 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("E:/PersonRecognitionDlib/model/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 = "E:/PersonRecognitionDlib/feature/features2_all.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.iloc[i, :])): features_someone_arr.append(csv_rd.iloc[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('E:/PersonRecognitionDlib/model/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 = 'E:/PersonRecognitionDlib/Person' # 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:LQH、YYQX、WY、WL... 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[0:]#人名删去第一个数字(用于视频输出标识) key_id += 1 # 播放欢迎光临音效 #playsound('D:/myworkspace/JupyterNotebook/People/music/welcome.wav') # print("May be person "+str(int(similar_person_num)+1)) # -----------筛选出人脸并保存到visitor文件夹------------ for i, d in enumerate(faces): x1 = d.top() if d.top() > 0 else 0 y1 = d.bottom() if d.bottom() > 0 else 0 x2 = d.left() if d.left() > 0 else 0 y2 = d.right() if d.right() > 0 else 0 face = img_rd[x1:y1,x2:y2] size = 64 face = cv2.resize(face, (size,size)) # 要存储visitor人脸图像文件的路径 path_visitors_save_dir = "E:/PersonRecognitionDlib/visitor/known" # 存储格式:2019-06-24-14-33-40LQH.jpg now_time = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) save_name = str(now_time)+str(name_namelist[k])+'.jpg' # print(save_name) # 本次图片保存的完整url save_path = path_visitors_save_dir+'/'+ save_name # 遍历visitor文件夹所有文件名 visitor_names = os.listdir(path_visitors_save_dir) visitor_name='' for name in visitor_names: # 名字切片到分钟数:2019-06-26-11-33-00LQH.jpg visitor_name=(name[0:16]+'-00'+name[19:]) # print(visitor_name) visitor_save=(save_name[0:16]+'-00'+save_name[19:]) # print(visitor_save) # 一分钟之内重复的人名不保存 if visitor_save!=visitor_name: cv2.imwrite(save_path, face) print('新存储:'+path_visitors_save_dir+'/'+str(now_time)+str(name_namelist[k])+'.jpg') else: print('重复,未保存!') else: # 播放无法识别音效 #playsound('D:/myworkspace/JupyterNotebook/People/music/sorry.wav') print("Unknown person") # -----保存图片------- # -----------筛选出人脸并保存到visitor文件夹------------ for i, d in enumerate(faces): x1 = d.top() if d.top() > 0 else 0 y1 = d.bottom() if d.bottom() > 0 else 0 x2 = d.left() if d.left() > 0 else 0 y2 = d.right() if d.right() > 0 else 0 face = img_rd[x1:y1,x2:y2] size = 64 face = cv2.resize(face, (size,size)) # 要存储visitor-》unknown人脸图像文件的路径 path_visitors_save_dir = "E:/PersonRecognitionDlib/visitor/unknown" # 存储格式:2019-06-24-14-33-40unknown.jpg now_time = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) # print(save_name) # 本次图片保存的完整url save_path = path_visitors_save_dir+'/'+ str(now_time)+'unknown.jpg' cv2.imwrite(save_path, face) print('新存储:'+path_visitors_save_dir+'/'+str(now_time)+'unknown.jpg') # 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()
参考链接
![Logo](https://devpress.csdnimg.cn/79de2bf0b7994defa4242ef90d5513fa.jpg)
开放原子开发者工作坊旨在鼓励更多人参与开源活动,与志同道合的开发者们相互交流开发经验、分享开发心得、获取前沿技术趋势。工作坊有多种形式的开发者活动,如meetup、训练营等,主打技术交流,干货满满,真诚地邀请各位开发者共同参与!
更多推荐
所有评论(0)