人脸检测项目（opencv+python）

调用opencv训练好的分类器（cv2.CascadeClassifier）实现人脸检测，

调用detectMultiScale()函数检测，调整函数的参数可以使检测结果更加精确，

把检测到的人脸等用矩形（或者圆形等其他图形）画出来。

1.image表示的是要检测的输入图像

2.objects表示检测到的人脸目标序列

3.scaleFactor表示每次图像尺寸减小的比例

4. minNeighbors表示每一个目标至少要被检测到3次才算是真的目标(因为周围的像素和不同的窗口大小都可以检测到人脸),

5.minSize为目标的最小尺寸

6.minSize为目标的最大尺寸

##图片检测

import cv2

def face_detected(im):
    im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
    face_detect = cv2.CascadeClassifier(\'D:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml\')
    face = face_detect.detectMultiScale(im_gray, 1.01, 5)
    for x, y, w, h in face:
        cv2.rectangle(im, (x, y), (x+w, y+h), color=(0, 0, 255))
    cv2.imshow(\'result\', im)


img = cv2.imread(\'E:/face_project/dzw.jpg\')
img = cv2.resize(img, (500, 400))
face_detected(img)


while True:
    if ord(\'q\') == cv2.waitKey(0):
        break
cv2.destroyWindow()

##视频检测

import cv2

def face_detected(im):
    im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
    face_detect = cv2.CascadeClassifier(\'D:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_default.xml\')
    face = face_detect.detectMultiScale(im_gray, 1.1)
    for x, y, w, h in face:
        cv2.rectangle(im, (x, y), (x+w, y+h), color=(0, 0, 255))
    cv2.imshow(\'result\', im)

cap = cv2.VideoCapture(0)




while True:
    flag, frame = cap.read()
    if not flag:
        break
    face_detected(frame)
    cv2.waitKey(1)
    # if ord(\'q\') == cv2.waitKey(1):
    #     break
cv2.destroyWindow(\'result\')
cap.release()

## 人脸识别的数据训练

import os
import cv2
import numpy as np
from PIL import Image
def getImageAndLabels(path):
    faceSamples = []

    ids = []

    imagesPath = [os.path.join(path, f) for f in os.listdir(path)]

    faceDetector = cv2.CascadeClassifier(\'D:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_default.xml\')

    for imPath in imagesPath:
        #用Image打开图片，模式”L“
        print(imPath)
        img = Image.open(imPath).convert(\'L\')
        img = img.resize((500, 400))
        print(img.size)
        #将图像转换成数组
        imgNumpy = np.array(img, \'uint8\')
        #获取人脸特征
        faces = faceDetector.detectMultiScale(imgNumpy)

        id = int(os.path.split(imPath)[1].split(\'.\')[0])

        for x, y, w, h in faces:
            ids.append(id)
            faceSamples.append(imgNumpy[y:y+h, x:x+w])
    print(ids)
    return faceSamples, ids

if __name__ == \'__main__\':
    path = "./data"
    # 获取训练数据
    faces, ids = getImageAndLabels(path)
    # 加载识别器
    # recognizer = cv2.face.LBPHFaceRecognizer_create()
    #训练
    recognizer = cv2.face.LBPHFaceRecognizer_create()
    # recognizer.train(faces,names)#np.array(ids)
    recognizer.train(faces, np.array(ids))
    # 保存文件
    recognizer.write(\'trainer/trainer.yml\')

## 人脸识别

# -*- coding: utf-8 -*-
# @Author  : 董张伟
# @Time    : 2021/10/4 20:17
# @Function:
import cv2
import numpy as np
import os
# coding=utf-8
import urllib
import urllib.request
import hashlib

#加载训练数据集文件
recogizer=cv2.face.LBPHFaceRecognizer_create()
recogizer.read(\'trainer/trainer.yml\')
names=[]
warningtime = 0

def md5(str):
    m = hashlib.md5()
    m.update(str.encode("utf8"))
    return m.hexdigest()

statusStr = {
    \'0\': \'短信发送成功\',
    \'-1\': \'参数不全\',
    \'-2\': \'服务器空间不支持,请确认支持curl或者fsocket,联系您的空间商解决或者更换空间\',
    \'30\': \'密码错误\',
    \'40\': \'账号不存在\',
    \'41\': \'余额不足\',
    \'42\': \'账户已过期\',
    \'43\': \'IP地址限制\',
    \'50\': \'内容含有敏感词\'
}


def warning():
    smsapi = "http://api.smsbao.com/"
    # 短信平台账号
    user = \'13******10\'
    # 短信平台密码
    password = md5(\'*******\')
    # 要发送的短信内容
    content = \'【报警】\n原因：检测到未知人员\n地点：xxx\'
    # 要发送短信的手机号码
    phone = \'*******\'

    data = urllib.parse.urlencode({\'u\': user, \'p\': password, \'m\': phone, \'c\': content})
    send_url = smsapi + \'sms?\' + data
    response = urllib.request.urlopen(send_url)
    the_page = response.read().decode(\'utf-8\')
    print(statusStr[the_page])

#准备识别的图片
def face_detect_demo(img):
    gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#转换为灰度
    face_detector=cv2.CascadeClassifier(\'D:/opencv/opencv/sources/data/haarcascades/haarcascade_frontalface_alt2.xml\')
    face=face_detector.detectMultiScale(gray,1.1,5,cv2.CASCADE_SCALE_IMAGE,(100,100),(300,300))
    #face=face_detector.detectMultiScale(gray)
    for x,y,w,h in face:
        cv2.rectangle(img,(x,y),(x+w,y+h),color=(0,0,255),thickness=2)
        cv2.circle(img,center=(x+w//2,y+h//2),radius=w//2,color=(0,255,0),thickness=1)
        # 人脸识别
        ids, confidence = recogizer.predict(gray[y:y + h, x:x + w])
        #print(\'标签id:\',ids,\'置信评分：\', confidence)
        cv2.putText(img, \'id:\'+str(ids)+"confidence:"+str(confidence), (30, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 0, 255), 1)
        if confidence > 80:
            global warningtime
            warningtime += 1
            if warningtime > 100:
               warning()
               warningtime = 0
            cv2.putText(img, \'unkonw\', (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 1)
        else:
            cv2.putText(img,str(names[ids-1]), (x + 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 255, 0), 1)
    cv2.imshow(\'result\',img)
    #print(\'bug:\',ids)

def name():
    path = \'./data\'
    #names = []
    imagePaths=[os.path.join(path,f) for f in os.listdir(path)]
    for imagePath in imagePaths:
       name = str(os.path.split(imagePath)[1].split(\'.\',2)[1])
       names.append(name)


cap=cv2.VideoCapture(0)
name()
while True:
    flag,frame=cap.read()
    if not flag:
        break
    face_detect_demo(frame)
    if ord(\' \') == cv2.waitKey(10):
        break
cv2.destroyAllWindows()
cap.release()