什么是人脸识别?
人脸识别,是基于人的脸部特征信息进行身份识别的一种生物识别技术。用摄像机或摄像头采集含有人脸的图像或视频流,并自动在图像中检测和跟踪人脸,进而对检测到的人脸进行脸部识别的一系列相关技术,通常也叫做人像识别、面部识别
人脸与人体的其它生物特征(指纹、虹膜等)一样与生俱来,它的唯一性和不易被复制的良好特性为身份鉴别提供了必要的前提,与其它类型的生物识别比较人脸识别具有如下特点:
非强制性:用户不需要专门配合人脸采集设备,几乎可以在无意识的状态下就可获取人脸图像,这样的取样方式没有“强制性”;
非接触性:用户不需要和设备直接接触就能获取人脸图像;
并发性:在实际应用场景下可以进行多个人脸的分拣、判断及识别;
除此之外,还符合视觉特性:“以貌识人”的特性,以及操作简单、结果直观、隐蔽性好等特点。
技术流程
人脸识别系统主要包括四个组成部分,分别为:人脸图像采集及检测、人脸图像预处理、人脸图像特征提取以及匹配与识别。
Opencv 人脸识别算法
opencv支持3种人脸识别的算法,分别是:
- Eigen Faces PCA(特征脸方法)
- Fisher Faces LDA(线性判别分析)
- Local Binary Pattern Histograms(LBPH 局部二值模式直方图)
详细介绍可以参照以下链接
https://blog.csdn.net/wanghz999/article/details/78817265
https://blog.csdn.net/u010006643/article/details/46417127
Opencv 在python环境下的安装
第一个demo
import cv2 as cv
#读入图片文件
src=cv.imread('textImg.jpg')
#创建一个名字加 “ input image ” 的窗口,
# 窗口可以根据图片大小自动调整
cv.namedWindow('input image',cv.WINDOW_AUTOSIZE)
#在窗口显示图片
cv.imshow('input image',src)
#等待用户操作
cv.waitKey(0)
#释放所有窗口
cv.destroyAllWindows()
图像基本属性有哪些:通道数目、高与宽、像素数据、图像类型
第一个摄像头操作
def video_demo():
# 打开0号摄像头,捕捉该摄像头实时信息
# 参数0代表摄像头的编号
# 有多个摄像头的情况下,可用编号打开摄像头
# 若是加载视频,则将参数改为视频路径,cv.VideoCapture加载视频是没有声音的,OpenCV只对视频的每一帧进行分析
capture = cv.VideoCapture(0)
while (True):
# 获取视频的返回值 ref 和视频中的每一帧 frame
ref, frame = capture.read()
# 加入该段代码将使拍出来的画面呈现镜像效果
# 第二个参数为视频是否上下颠倒 0为上下颠倒 1为不进行上下颠倒
frame = cv.flip(frame, 1)
# 将每一帧在窗口中显示出来
cv.imshow("video", frame)
# 设置视频刷新频率,单位为毫秒
# 返回值为键盘按键的值
c = cv.waitKey(50)
# 27为 Esc 按键的返回值
if c == 27:
break
#每个像素点所占字节位数
print(image.dtype)
人脸识别所需API
# 人脸识别分类器 使用opencv自带的人脸分类器
faceCascade=cv2.CascadeClassifier(r'C:\python3.7\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml')
# 开启摄像头 默认笔记本的摄像头是第0号摄像头,如果有外置摄像头,并向启动就是1
cap = cv2.VideoCapture(0)
# 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()
# 人脸检测
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.05,
minNeighbors=5,
minSize=(32, 32)
)
人脸识别分类器所在位置,复制到当前工作目录下即可。
关键函数定义
void CascadeClassifier::detectMultiScale( const Mat& image, vector<Rect>& objects,
double scaleFactor, int minNeighbors,
int flags, Size minObjectSize, Size maxObjectSize)
{
vector<int> fakeLevels;
vector<double> fakeWeights;
detectMultiScale( image, objects, fakeLevels, fakeWeights, scaleFactor,
minNeighbors, flags, minObjectSize, maxObjectSize, false );
}
# 画矩形
cv2.rectangle(img, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2)
第一个参数:img是原图
第二个参数:(x,y)是矩阵的左上点坐标
第三个参数:(x+w,y+h)是矩阵的右下点坐标
第四个参数:(0,255,0)是画线对应的rgb颜色
第五个参数:2是所画的线的宽度
#显示视频窗口
cv2.imshow('video', img)
#获取按键指令
k = cv2.waitKey(1)
#关闭摄像头
cap.release()
#销毁全部窗体
cv2.destroyAllWindows()
# 转为灰度图片
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 保存图像
cv2.imwrite(path, src)
#打开图片,并转化为灰度
PIL_img = Image.open(imagePath).convert('L')
模块搭建
- 人脸识别之找到你的脸
1.1. 流程图:
1.2. 代码实现
import numpy as np
import cv2
# 人脸识别分类器
faceCascade = cv2.CascadeClassifier(r'haarcascade_frontalface_default.xml')
# 识别眼睛的分类器
eyeCascade = cv2.CascadeClassifier(r'haarcascade_eye.xml')
# 开启摄像头
cap = cv2.VideoCapture(0)
ok = True
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: # press 'ESC' to quit
break
cap.release()
cv2.destroyAllWindows()
1.3 效果图
- 人脸识别之预训练图像采集
2.1. 流程图:
2.2. 代码实现:
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
cap = cv2.VideoCapture(0)
face_detector = cv2.CascadeClassifier('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 >= 100: # 得到1000个样本后退出摄像
break
# 关闭摄像头
cap.release()
cv2.destroyAllWindows()
- 人脸识别之训练机器:识别脸特征
3.1. 流程图
3.2. 代码实现
import numpy as np
from PIL import Image
import os
import cv2
# 人脸数据路径
path = 'Facedata'
recognizer = cv2.face.LBPHFaceRecognizer_create()
detector = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
def getImagesAndLabels(path):
imagePaths = [os.path.join(path, f) for f in os.listdir(path)] # join函数的作用?
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('Training faces. It will take a few seconds. Wait ...')
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))))
- 人脸识别之根据记忆与现实进行匹配
4.1. 流程图
4.2. 代码实现
import cv2
recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('face_trainer/trainer.yml')
cascadePath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascadePath)
font = cv2.FONT_HERSHEY_SIMPLEX
idnum = 0
names = ['zongyong', 'zhangmin','shanglanqing']
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])
print(idnum)
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()
语音模块编写
需要安装 pyttsx3库
import pyttsx3
engine = pyttsx3.init()
engine.say('Hello, good morning')
engine.runAndWait()
整合
mport cv2
import os
import numpy as np
from PIL import Image
def getFace(cap):
# 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
#cap = cv2.VideoCapture(0)
face_detector = cv2.CascadeClassifier('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 >= 100: # 得到1000个样本后退出摄像
break
# 关闭摄像头
# cap.release()
# cv2.destroyAllWindows()
def getImagesAndLabels(path,detector):
imagePaths = [os.path.join(path, f) for f in os.listdir(path)] # join函数的作用?
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
def trainFace():
# 人脸数据路径
path = 'Facedata'
recognizer = cv2.face.LBPHFaceRecognizer_create()
detector = cv2.CascadeClassifier("haarcascade_frontalface_default.xml")
print('Training faces. It will take a few seconds. Wait ...')
faces, ids = getImagesAndLabels(path,detector)
recognizer.train(faces, np.array(ids))
recognizer.write(r'face_trainer\trainer.yml')
print("{0} faces trained. Exiting Program".format(len(np.unique(ids))))
def checkFace(cam):
recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('face_trainer/trainer.yml')
cascadePath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascadePath)
font = cv2.FONT_HERSHEY_SIMPLEX
idnum = 0
names = ['zongyong', 'zhangmin', 'shanglanqing']
#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])
print(idnum)
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()
if __name__ == '__main__':
cam = cv2.VideoCapture(0)
getFace(cam)
trainFace()
checkFace(cam)