快捷導(dǎo)航

詳解基于Facecognition+Opencv快速搭建人臉識(shí)別及跟蹤應(yīng)用

更新時(shí)間：2021年01月21日 09:04:46 作者：HeroMan_BY

這篇文章主要介紹了詳解基于Facecognition+Opencv快速搭建人臉識(shí)別及跟蹤應(yīng)用，文中通過(guò)示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值，需要的朋友們下面隨著小編來(lái)一起學(xué)習(xí)學(xué)習(xí)吧

人臉識(shí)別技術(shù)已經(jīng)相當(dāng)成熟，面對(duì)滿大街的人臉識(shí)別應(yīng)用，像單位門禁、刷臉打卡、App解鎖、刷臉支付、口罩檢測(cè)........

作為一個(gè)圖像處理的愛好者，怎能放過(guò)人臉識(shí)別這一環(huán)呢！調(diào)研開搞，發(fā)現(xiàn)了超實(shí)用的Facecognition！現(xiàn)在和大家分享下~~

Facecognition人臉識(shí)別原理大體可分為：

1、通過(guò)hog算子定位人臉，也可以用cnn模型，但本文沒試過(guò)；

2、Dlib有專門的函數(shù)和模型，實(shí)現(xiàn)人臉68個(gè)特征點(diǎn)的定位。通過(guò)圖像的幾何變換（仿射、旋轉(zhuǎn)、縮放），使各個(gè)特征點(diǎn)對(duì)齊（將眼睛、嘴等部位移到相同位置）；

3、訓(xùn)練一個(gè)神經(jīng)網(wǎng)絡(luò)，將輸入的臉部圖像生成為128維的預(yù)測(cè)值。訓(xùn)練的大致過(guò)程為：將同一人的兩張不同照片和另一人的照片一起喂入神經(jīng)網(wǎng)絡(luò)，不斷迭代訓(xùn)練，使同一人的兩張照片編碼后的預(yù)測(cè)值接近，不同人的照片預(yù)測(cè)值拉遠(yuǎn)；

4、將陌生人臉預(yù)測(cè)為128維的向量，與人臉庫(kù)中的數(shù)據(jù)進(jìn)行比對(duì)，找出閾值范圍內(nèi)歐氏距離最小的人臉，完成識(shí)別。

1 開發(fā)環(huán)境

PyCharm： PyCharm Community Edition 2020.3.2 x64

Python：Python 3.8.7

Opencv：opencv-python 4.5.1.48

Facecognition：1.3.0

Dlb：dlb 0.5.0

2 環(huán)境搭建

本文不做PyCharm和Python安裝，這個(gè)自己搞不定，就別玩了~

pip install opencv-python
pip install face-recognition
pip install face-recognition-models
pip install dlb

3 打造自己的人臉庫(kù)

通過(guò)opencv、facecogniton定位人臉并保存人臉頭像，生成人臉數(shù)據(jù)集，代碼如下：

import face_recognition
import cv2
import os
 
def builddataset():
  Video_face = cv2.VideoCapture(0)
  num=0
  while True:
    flag, frame = Video_face.read();
    if flag:
      cv2.imshow('frame', frame)
      cv2.waitKey(2)
    else:
      break
    face_locations = face_recognition.face_locations(frame)
    if face_locations:
      x_face = frame[face_locations[0][0]-50:face_locations[0][2]+50, face_locations[0][3]-50:face_locations[0][1]+50];
      #x_face = cv2.resize(x_face, dsize=(200, 200));
      bo_photo = cv2.imwrite("%s\%d.jpg" % ("traindataset/ylb", num), x_face);
      print("保存成功:%d" % num)
      num=num+1
    else:
      print("****未檢查到頭像****")
 
  Video_face.release()
 
if __name__ == '__main__':
  builddataset();
  pass

4、模型訓(xùn)練與保存

通過(guò)數(shù)據(jù)集進(jìn)行訓(xùn)練，得到人臉識(shí)別碼，以numpy數(shù)據(jù)形式保存（人臉識(shí)別碼）模型

 def __init__(self, trainpath,labelname,modelpath, predictpath):
    self.trainpath = trainpath
    self.labelname = labelname
    self.modelpath = modelpath
    self.predictpath = predictpath
 
  # no doc
  def train(self, trainpath, modelpath):
    encodings = []
    dirs = os.listdir(trainpath)
    for k,dir in enumerate(dirs):
      filelist = os.listdir(trainpath+'/'+dir)
      for i in range(0, len(filelist)):
        imgname = trainpath + '/'+dir+'/%d.jpg' % (i)
        picture_of_me = face_recognition.load_image_file(imgname)
        face_locations = face_recognition.face_locations(picture_of_me)
        if face_locations:
          print(face_locations)
          my_face_encoding = face_recognition.face_encodings(picture_of_me,     
                    face_locations)[0]
          encodings.append(my_face_encoding)
    if encodings:
      numpy.save(modelpath, encodings)
      print(len(encodings))
      print("model train is sucess")
    else:
      print("model train is failed")

5、人臉識(shí)別及跟蹤

通過(guò)opencv啟動(dòng)攝像頭并獲取視頻，加載訓(xùn)練好模型完成識(shí)別及跟蹤，為避免視頻卡頓設(shè)置了隔幀處理。

  def predicvideo(self,names,model):
    Video_face = cv2.VideoCapture(0)
    num=0
    recongnition=[]
    unknown_face_locations=[]
    while True:
      flag, frame = Video_face.read();
      frame = cv2.flip(frame, 1) # 鏡像操作
      num=num+1
      if flag:
        self.predictpeople(num, recongnition,unknown_face_locations,frame, names, encodings)
      else:
        break
    Video_face.release()
 
  def predictpeople(self, condition,recongnition,unknown_face_locations,unknown_picture,labels,encodings):
    if condition%5==0:
      face_locations = face_recognition.face_locations(unknown_picture)
      unknown_face_encoding = face_recognition.face_encodings(unknown_picture,face_locations)
      unknown_face_locations.clear()
      recongnition.clear()
      for index, value in enumerate(unknown_face_encoding):
        unknown_face_locations.append(face_locations[index])
        results = face_recognition.compare_faces(encodings, value, 0.4)
        splitresult = numpy.array_split(results, len(labels))
        trueNum=[]
        a1 = ''
        for item in splitresult:
          number = numpy.sum(item)
          trueNum.append(number)
        if numpy.max(trueNum) > 0:
          id = numpy.argsort(trueNum)[-1]
          a1 = labels[id]
          cv2.rectangle(unknown_picture,
                 pt1=(unknown_face_locations[index][1], unknown_face_locations[index][0]),
                 pt2=(unknown_face_locations[index][3], unknown_face_locations[index][2]),
                 color=[0, 0, 255],
                 thickness=2);
          cv2.putText(unknown_picture, a1,
                (unknown_face_locations[index][1], unknown_face_locations[index][0]),
                cv2.FONT_ITALIC, 1, [0, 0, 255], 2);
        else:
          a1 = "unkown"
          cv2.rectangle(unknown_picture,
                 pt1=(unknown_face_locations[index][1], unknown_face_locations[index][0]),
                 pt2=(unknown_face_locations[index][3], unknown_face_locations[index][2]),
                 color=[0, 0, 255],
                 thickness=2);
          cv2.putText(unknown_picture, a1,
                (unknown_face_locations[index][1], unknown_face_locations[index][0]),
                cv2.FONT_ITALIC, 1, [0, 0, 255], 2);
        recongnition.append(a1)
    else:
      self.drawRect(unknown_picture,recongnition,unknown_face_locations)
    cv2.imshow('face', unknown_picture)
    cv2.waitKey(1)

6、結(jié)語(yǔ)

通過(guò)opencv啟動(dòng)攝像頭并獲取實(shí)時(shí)視頻，為避免過(guò)度卡頓采取隔幀處理；利用Facecognition實(shí)現(xiàn)模型的訓(xùn)練、保存、識(shí)別，二者結(jié)合實(shí)現(xiàn)了實(shí)時(shí)視頻人臉的多人識(shí)別及跟蹤，希望對(duì)大家有所幫助~！

到此這篇關(guān)于詳解基于Facecognition+Opencv快速搭建人臉識(shí)別及跟蹤應(yīng)用的文章就介紹到這了,更多相關(guān)Facecognition+Opencv人臉識(shí)別內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: