[人脸识别]09-人脸模型训练

1.程序代码

#导入CV模块

import cv2 as cv
import os
from PIL import Image
import numpy as np


def getImageAndLabels(path):

    #存储人脸数据
    facesSamples=[]
    #存储姓名数据
    ids=[]
    # 存储图片信息
    imagePaths=[ os.path.join(path,f) for f in os.listdir(path)]

    print("files:",imagePaths)

    #加载分类器
    face_detector=cv.CascadeClassifier(cv.data.haarcascades+"haarcascade_frontalface_default.xml")

    #遍历列表中的图片
    for imagePath in imagePaths:
        #打开图片，灰度化，PIL有九种不同模式：1,l,p,rgb,rgba,cmyk,yCbCr,I,F
        PIL_img=Image.open(imagePath).convert('L')
        #将图片转换为数组，以黑白深浅
        img_numpy=np.array(PIL_img,'uint8')
        #获取人脸特征
        faces=face_detector.detectMultiScale(img_numpy)
        #获取每张图片的ID和新名
        id=int(os.path.split(imagePath)[1].split('.')[0])

        #预防无面容照片
        for x,y,w,h in faces:
            ids.append(id)
            facesSamples.append(img_numpy[y:y+h,x:x+w])
        print('id',id)
    print('fs',facesSamples)

    return facesSamples,ids

if __name__ == '__main__':

    #图片路径
    root = os.getcwd()
    path=root+"/jm/"

    print("path:", path)

    #获取图像数组,id
    faces,ids=getImageAndLabels(path)

    #获取训练对象
    recognizer=cv.face.LBPHFaceRecognizer_create()

    #执行训练
    recognizer.train(faces,np.array(ids))

    #保存训练结果
    print("write:", root+"/trainer/trainer.yml")
    recognizer.write(root+"/trainer/trainer.yml")

2结果

.