使用python3.7和opencv4.1来实现人脸识别和人脸特征比对以及模型训练
OpenCV4.1已经发布将近一年了,其人脸识别速度和性能有了一定的提高,这里我们使用opencv来做一个实时活体面部识别的demo
首先安装一些依赖的库
pip install opencv-python pip install opencv-contrib-python pip install numpy pip install pillow需要注意一点,最好将pip设置国内的阿里云的源,否则安装会很慢
win10在用户目录下创建一个pip文件夹,然后在pip文件夹内创建一个pip.ini文件,文件内容如下
[global] trusted-host = mirrors.aliyun.com index-url = http://mirrors.aliyun.com/pypi/simple这样就可以用国内的源来下载安装包
一开始,我们可以简单的在摄像头中识别人的脸部和眼镜,原来就是用opencv内置的分类器,对直播影像中的每一帧进行扫描
import numpy as np import cv2 from settings import src # 人脸识别 faceCascade = cv2.CascadeClassifier(src+'haarcascade_frontalface_default.xml') # 识别眼睛 eyeCascade = cv2.CascadeClassifier(src+'haarcascade_eye.xml') # 开启摄像头 cap = cv2.VideoCapture(0) ok = True result = [] while ok: # 读取摄像头中的图像,ok为是否读取成功的判断参数 ok, img = cap.read() # 转换成灰度图像 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 人脸检测 faces = faceCascade.detectMultiScale( gray, scaleFactor=1.2, minNeighbors=5, minSize=(32, 32) ) # 在检测人脸的基础上检测眼睛 for (x, y, w, h) in faces: fac_gray = gray[y: (y+h), x: (x+w)] result = [] eyes = eyeCascade.detectMultiScale(fac_gray, 1.3, 2) # 眼睛坐标的换算,将相对位置换成绝对位置 for (ex, ey, ew, eh) in eyes: result.append((x+ex, y+ey, ew, eh)) # 画矩形 for (x, y, w, h) in faces: cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2) for (ex, ey, ew, eh) in result: cv2.rectangle(img, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2) cv2.imshow('video', img) k = cv2.waitKey(1) if k == 27: #按 'ESC' to quit break cap.release() cv2.destroyAllWindows()第二步,就是为模型训练收集训练数据,还是通过摄像头逐帧来收集,在脚本运行过程中,会提示输入用户id,请从0开始输入,即第一个人的脸的数据id为0,第二个人的脸的数据id为1,运行一次可收集一张人脸的数据
脚本时间可能会比较长,会将摄像头每一帧的数据进行保存,保存路径在项目目录下的Facedat目录,1200个样本后退出摄像录制
import cv2 import os # 调用笔记本内置摄像头,所以参数为0,如果有其他的摄像头可以调整参数为1,2 from settings import src cap = cv2.VideoCapture(0) face_detector = cv2.CascadeClassifier(src+'haarcascade_frontalface_default.xml') face_id = input('n enter user id:') print('n Initializing face capture. Look at the camera and wait ...') count = 0 while True: # 从摄像头读取图片 sucess, img = cap.read() # 转为灰度图片 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 检测人脸 faces = face_detector.detectMultiScale(gray, 1.3, 5) for (x, y, w, h) in faces: cv2.rectangle(img, (x, y), (x+w, y+w), (255, 0, 0)) count += 1 # 保存图像 cv2.imwrite("./Facedata/User." + str(face_id) + '.' + str(count) + '.jpg', gray[y: y + h, x: x + w]) cv2.imshow('image', img) # 保持画面的持续。 k = cv2.waitKey(1) if k == 27: # 通过esc键退出摄像 break elif count >= 1200: # 得到1000个样本后退出摄像 break # 关闭摄像头 cap.release() cv2.destroyAllWindows()
第三步,对收集下来的人脸数据进行模型训练,提取特征,训练后,会将特征数据保存在项目目录中的face_trainer文件夹下面
import numpy as np from PIL import Image import os import cv2 from settings import src # 人脸数据路径 path = 'Facedata' recognizer = cv2.face.LBPHFaceRecognizer_create() detector = cv2.CascadeClassifier(src+"haarcascade_frontalface_default.xml") def getImagesAndLabels(path): imagePaths = [os.path.join(path, f) for f in os.listdir(path)] faceSamples = [] ids = [] for imagePath in imagePaths: PIL_img = Image.open(imagePath).convert('L') # convert it to grayscale img_numpy = np.array(PIL_img, 'uint8') id = int(os.path.split(imagePath)[-1].split(".")[1]) faces = detector.detectMultiScale(img_numpy) for (x, y, w, h) in faces: faceSamples.append(img_numpy[y:y + h, x: x + w]) ids.append(id) return faceSamples, ids print('训练需要一定时间,请耐心等待....') faces, ids = getImagesAndLabels(path) recognizer.train(faces, np.array(ids)) recognizer.write(r'./face_trainer/trainer.yml') print("{0} faces trained. Exiting Program".format(len(np.unique(ids))))最后一步,人脸测试,我们将摄像头中的人脸和模型中的特征进行比对,用来判断是否为本人
import cv2 from settings import src recognizer = cv2.face.LBPHFaceRecognizer_create() recognizer.read('./face_trainer/trainer.yml') cascadePath = src+"haarcascade_frontalface_default.xml" faceCascade = cv2.CascadeClassifier(cascadePath) font = cv2.FONT_HERSHEY_SIMPLEX idnum = 0 names = ['andonghui', 'admin'] cam = cv2.VideoCapture(0) minW = 0.1*cam.get(3) minH = 0.1*cam.get(4) while True: ret, img = cam.read() gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) faces = faceCascade.detectMultiScale( gray, scaleFactor=1.2, minNeighbors=5, minSize=(int(minW), int(minH)) ) for (x, y, w, h) in faces: cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) idnum, confidence = recognizer.predict(gray[y:y+h, x:x+w]) if confidence < 100: idnum = names[idnum] confidence = "{0}%".format(round(100 - confidence)) else: idnum = "unknown" confidence = "{0}%".format(round(100 - confidence)) cv2.putText(img, str(idnum), (x+5, y-5), font, 1, (0, 0, 255), 1) cv2.putText(img, str(confidence), (x+5, y+h-5), font, 1, (0, 0, 0), 1) cv2.imshow('camera', img) k = cv2.waitKey(10) if k == 27: break cam.release() cv2.destroyAllWindows()整个流程并不复杂,可以让opencv初学者感受一下人脸识别底层的逻辑,说明自研应用还是有一定可操作性的,并不是涉及机器学习的技术就动辄使用百度,阿里云等三方支持。
最后,送上人脸识别项目地址:
https://gitee.com/QiHanXiBei/face_get/tree/master
-
Next Post简短截说阐述redis中事务的使用
-
Previous Post基于Vue.js2.6结合h5来实现视频播放画中画技术(Picture-in-Picture)