目录
前言
随着人工智能的不断发展,机器学习和深度学习这门技术也越来越重要,一时间成为码农的学习热点。下面将使用深度学习技术开发一个人脸识别系统。之前使用 Tensorflow1.5 完成人脸识别(之前版本的链接: 手把手教你完成深度学习人脸识别系统),现在更新到 Tensorflow2.7 版本,我已经改写完成了,更新内容如下:
- 加入 Flask 框架完成一个简单的 web 版人脸识别
- Tensorflow1.5 改成 Tensorflow 2.7
- 数据预处理代码更加自动
下面直接展示结果吧:
一、系统总流程设计
二、环境安装
手把手教学视频:
链接: link
建议所有库的版本跟我一样,以免出错
python=3.8
tensorflow==2.7(这个版本一定要跟我一样的)
1. 创建虚拟环境
conda create -n py38 python=3.8
激活环境
activate py38
2.安装其他库
(1)单独安装 pyqt5,命令如下
pip install pyqt5
(2)单独安装 tensorflow,要么安装 gpu 版本或者 cpu 版本,下面给出各自的安装教程
如果安装 gpu 版本,电脑必须有英伟达显卡,并且先安装对应版本的 cuda 和 cudnn,安装教程看这篇文章: cuda和cudnn的安装教程(全网最详细保姆级教程),我安装的 cuda 版本是11.3,cudnn 版本是 8.2,建议安装跟我一样,避免报错
安装完 cuda 和 cudnn 之后,输入如下命令来安装 tensorflow gpu 版本 :
pip install tensorflow_gpu==2.7.0
测试tensorflow gpu 是否能用,代码如下:
# -*- coding: utf-8 -*-"""
@Auth : 挂科边缘
@File :Test.py
@IDE :PyCharm
@Motto:学习新思想,争做新青年
@Email :[email protected]
"""import tensorflow as tf
a = tf.test.is_built_with_cuda()# 判断CUDA是否可以用
b = tf.test.is_gpu_available(
cuda_only=False,
min_cuda_compute_capability=None)# 判断GPU是否可以用print(a)print(b)
输出两个True证明能用,如下图所示
如果安装 cpu 版本就简单了,不用安装cuda和cudnn,直接输入下面命令安装就行,命令如下:
pip install tensorflow-cpu==2.7.0
之后安装 requirements.txt 配置文件,命令如下:
pip install -r requirements.txt
安装完环境你已经成功一大把了,看到这里点个赞赞鼓励一下
报错了并解决的方法
报错:AttributeError: ‘str‘ object has no attribute ‘decode‘
降低h5py版本
解决方法:
pip install h5py==2.10.0
报错:ImportError: cannot import name ‘secure_filename’ from ‘werkzeug’
解决方法,进入到 flask_uploads.py 文件
把圈起来的代码改成下面的:
from werkzeug.utils import secure_filename
from werkzeug.datastructures import FileStorage
三、模型搭建
1.采集数据集
使用摄像头进行采集
代码可以直接运行,getdata.py代码如下:
注意:25行 cap = cv2.VideoCapture(1)的改为 cap = cv2.VideoCapture(0),0代表本电脑自带摄像头,1代码其他外接摄像头:
# encoding:utf-8'''
功能: Python opencv调用摄像头获取个人图片
使用方法:
启动摄像头后需要借助键盘输入操作来完成图片的获取工作
c(change): 生成存储目录
p(photo): 执行截图
q(quit): 退出拍摄
'''import os
import cv2
defcameraAutoForPictures(saveDir='data/'):'''
调用电脑摄像头来自动获取图片
'''ifnot os.path.exists(saveDir):
os.makedirs(saveDir)
count =1
cap = cv2.VideoCapture(1)
width, height, w =640,480,360
cap.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
crop_w_start =(width - w)//2
crop_h_start =(height - w)//2print('width: ', width)print('height: ', height)whileTrue:
ret, frame = cap.read()
frame = frame[crop_h_start:crop_h_start + w, crop_w_start:crop_w_start + w]
frame = cv2.flip(frame,1, dst=None)
cv2.imshow("capture", frame)
action = cv2.waitKey(1)&0xFFif action ==ord('c'):
saveDir =input(u"请输入新的存储目录:")ifnot os.path.exists(saveDir):
os.makedirs(saveDir)elif action ==ord('p'):
cv2.imwrite("%s/%d.jpg"%(saveDir, count), cv2.resize(frame,(224,224), interpolation=cv2.INTER_AREA))print(u"%s: %d 张图片"%(saveDir, count))
count +=1if action ==ord('q'):break
cap.release()
cv2.destroyAllWindows()if __name__ =='__main__':# xxx替换为自己的名字
cameraAutoForPictures(saveDir=u'data/1/')
2. 数据预处理
代码可以直接运行,new_data_preparation.py代码如下:
# -*- coding: utf-8 -*-"""
@Auth : 挂科边缘
@File :new_data_preparation.py
@IDE :PyCharm
@Motto:学习新思想,争做新青年
@Email :[email protected]
"""'''
功能: 图像的数据预处理、标准化部分
'''import os
import cv2
import time
defreadAllImg(path,*suffix):'''
基于后缀读取文件
'''
resultArray =[]try:for root, dirs, files in os.walk(path):forfilein files:if endwith(file, suffix):
document = os.path.join(root,file)
img = cv2.imread(document)
resultArray.append((document, img))except IOError:print("Error")else:print("读取成功")return resultArray
defendwith(s,*endstring):'''
对字符串的后缀进行匹配
'''returnany(map(s.endswith, endstring))defreadPicSaveFace(sourcePath, objectPath,*suffix):'''
图片标准化与存储
'''ifnot os.path.exists(objectPath):
os.makedirs(objectPath)try:
allImages = readAllImg(sourcePath,*suffix)
face_cascade = cv2.CascadeClassifier('config/haarcascade_frontalface_alt.xml')
count =0for document, img in allImages:if img isnotNone:
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray,1.3,5)for(x, y, w, h)in faces:
face = cv2.resize(gray[y:y + h, x:x + w],(200,200))# 创建与sourcePath子目录对应的objectPath子目录
relativePath = os.path.relpath(document, sourcePath)
subdir = os.path.dirname(relativePath)
saveDir = os.path.join(objectPath, subdir)ifnot os.path.exists(saveDir):
os.makedirs(saveDir)
timestamp =str(int(time.time()))
fileName =f'{timestamp}_{count}.jpg'
cv2.imwrite(os.path.join(saveDir, fileName), face)
count +=1except Exception as e:print("Exception:", e)else:print(f'已处理 {count} 张人脸,保存到 {objectPath}')if __name__ =='__main__':print('数据处理开始!!!')
readPicSaveFace('data','dataset','.jpg','.JPG','.png','.PNG','.tiff','.TIFF')
3.构建模型和训练
代码可以直接运行,train_model.py代码如下:
keras搭建cnn网络模型提取人脸特征
# -*- coding: utf-8 -*-"""
@Auth : 挂科边缘
@File :train_model.py
@IDE :PyCharm
@Motto:学习新思想,争做新青年
@Email :[email protected]
"""'''
功能: 构建人脸识别模型
'''import os
import cv2
import random
import numpy as np
from tensorflow.keras.models import Sequential, load_model
from sklearn.model_selection import train_test_split
from tensorflow.keras.layers import Dense, Activation, Conv2D, MaxPooling2D, Flatten
from tensorflow.keras.utils import to_categorical
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
os.environ['CUDA_VISIBLE_DEVICES']='0'classDataSet(object):'''
用于存储和格式化读取训练数据的类
'''def__init__(self, path):'''
初始化
'''
self.num_classes =None
self.X_train =None
self.X_test =None
self.Y_train =None
self.Y_test =None
self.img_size =128
self.extract_data(path)defextract_data(self, path):'''
抽取数据
'''
imgs, labels, counter = read_file(path)
X_train, X_test, y_train, y_test = train_test_split(imgs, labels, test_size=0.2, random_state=random.randint(0,100))
X_train = X_train.reshape(X_train.shape[0], self.img_size, self.img_size,1)/255.0
X_test = X_test.reshape(X_test.shape[0], self.img_size, self.img_size,1)/255.0
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
Y_train = to_categorical(y_train, num_classes=counter)
Y_test = to_categorical(y_test, num_classes=counter)
self.X_train = X_train
self.X_test = X_test
self.Y_train = Y_train
self.Y_test = Y_test
self.num_classes = counter
defcheck(self):'''
校验
'''print('num of dim:', self.X_test.ndim)print('shape:', self.X_test.shape)print('size:', self.X_test.size)print('num of dim:', self.X_train.ndim)print('shape:', self.X_train.shape)print('size:', self.X_train.size)print(np.isnan(dataset.X_train).sum())print(np.isnan(dataset.X_test).sum())defendwith(s,*endstring):'''
对字符串的后续和标签进行匹配
'''
resultArray =map(s.endswith, endstring)ifTruein resultArray:returnTrueelse:returnFalsedefread_file(path):'''
图片读取
'''
img_list =[]
label_list =[]
dir_counter =0
IMG_SIZE =128for child_dir in os.listdir(path):
child_path = os.path.join(path, child_dir)for dir_image in os.listdir(child_path):if endwith(dir_image,'jpg'):
img = cv2.imread(os.path.join(child_path, dir_image))
resized_img = cv2.resize(img,(IMG_SIZE, IMG_SIZE))
recolored_img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2GRAY)
img_list.append(recolored_img)
label_list.append(dir_counter)
dir_counter +=1
img_list = np.array(img_list)return img_list, label_list, dir_counter
defread_name_list(path):'''
读取训练数据集
'''
name_list =[]for child_dir in os.listdir(path):
name_list.append(child_dir)return name_list
classModel(object):'''
人脸识别模型
'''
FILE_PATH ="./models/face.h5"
IMAGE_SIZE =128def__init__(self):
self.model =Nonedefread_trainData(self, dataset):
self.dataset = dataset
defbuild_model(self):
self.model = Sequential()
self.model.add(
Conv2D(
filters=32,
kernel_size=(5,5),
padding='same',
input_shape=self.dataset.X_train.shape[1:]))
self.model.add(Activation('relu'))
self.model.add(
MaxPooling2D(
pool_size=(2,2),
strides=(2,2),
padding='same'))
self.model.add(Conv2D(filters=64, kernel_size=(5,5), padding='same'))
self.model.add(Activation('relu'))
self.model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'))
self.model.add(Flatten())
self.model.add(Dense(1024))
self.model.add(Activation('relu'))
self.model.add(Dense(self.dataset.num_classes))
self.model.add(Activation('softmax'))
self.model.summary()deftrain_model(self,epochs,batch_size):
self.model.compile(
optimizer='sgd',
loss='categorical_crossentropy',
metrics=['accuracy'])
self.model.fit(self.dataset.X_train, self.dataset.Y_train, epochs=epochs, batch_size=batch_size)defevaluate_model(self):print('\nTesting---------------')
loss, accuracy = self.model.evaluate(self.dataset.X_test, self.dataset.Y_test)print('test loss:', loss)print('test accuracy:', accuracy)defsave(self, file_path=FILE_PATH):print('Model Saved Finished!!!')
self.model.save(file_path)defload(self, file_path=FILE_PATH):print('Model Loaded Successful!!!')
self.model = load_model(file_path)defpredict(self, img):
img = img.reshape((1, self.IMAGE_SIZE, self.IMAGE_SIZE,1))
img = img.astype('float32')
img = img /255.0
result = self.model.predict(img)
max_index = np.argmax(result)return max_index, result[0][max_index]if __name__ =='__main__':
dataset = DataSet('dataset/')
model = Model()
model.read_trainData(dataset)
model.build_model()
model.train_model(epochs=10,batch_size=32)
model.evaluate_model()
model.save()
五、摄像头测试
代码可以直接运行,Demo.py代码如下:
new_names 对应文件夹人脸的顺序
#encoding:utf-8from __future__ import division
import numpy
'''
功能: 人脸识别摄像头视频流数据实时检测模块
'''from PIL import Image, ImageDraw, ImageFont
import os
import cv2
from train_model import Model
threshold=0.7# 如果模型认为概率高于70%则显示为模型中已有的人物# 新的名字列表
new_names =["张三","李四"]# 解决cv2.putText绘制中文乱码defcv2ImgAddText(img2, text, left, top, textColor=(0,0,255), textSize=20):ifisinstance(img2, numpy.ndarray):# 判断是否OpenCV图片类型
img2 = Image.fromarray(cv2.cvtColor(img2, cv2.COLOR_BGR2RGB))# 创建一个可以在给定图像上绘图的对象
draw = ImageDraw.Draw(img2)# 字体的格式
fontStyle = ImageFont.truetype(r"C:\WINDOWS\FONTS\MSYH.TTC", textSize, encoding="utf-8")# 绘制文本
draw.text((left, top), text, textColor, font=fontStyle)# 转换回OpenCV格式return cv2.cvtColor(numpy.asarray(img2), cv2.COLOR_RGB2BGR)classCamera_reader(object):def__init__(self):
self.model=Model()
self.model.load()
self.img_size=128defbuild_camera(self):'''
调用摄像头来实时人脸识别
'''
face_cascade = cv2.CascadeClassifier('config/haarcascade_frontalface_alt.xml')
cameraCapture=cv2.VideoCapture(0)
success, frame=cameraCapture.read()while success and cv2.waitKey(1)==-1:
success,frame=cameraCapture.read()
gray=cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces=face_cascade.detectMultiScale(gray,1.3,5)for(x,y,w,h)in faces:
ROI=gray[x:x+w,y:y+h]
ROI=cv2.resize(ROI,(self.img_size, self.img_size),interpolation=cv2.INTER_LINEAR)
label,prob=self.model.predict(ROI)print(label)if prob > threshold:
show_name = new_names[label]else:
show_name ="陌生人"# cv2.putText(frame, show_name, (x,y-20),cv2.FONT_HERSHEY_SIMPLEX,1,255,2)# 在图像上绘制中文字符# 解决cv2.putText绘制中文乱码
frame = cv2ImgAddText(frame, show_name, x +5, y -30,)
frame=cv2.rectangle(frame,(x,y),(x+w,y+h),(255,0,0),2)
cv2.imshow("Camera", frame)else:
cameraCapture.release()
cv2.destroyAllWindows()if __name__ =='__main__':
camera=Camera_reader()
camera.build_camera()
六、web界面搭建与pyqt界面搭建
web 界面采用 Flask 框架,主要实现图片识别功能,运行MainWeb.py即可在浏览器访问了,地址是:http://127.0.0.1:5000/upload
MainWeb.py代码如下:
# -*- coding: utf-8 -*-"""
@Auth : 挂科边缘
@File :Test.py
@IDE :PyCharm
@Motto:学习新思想,争做新青年
@Email :[email protected]
@qq :179958974
"""import os
import time
import cv2
import numpy as np
from PIL import Image, ImageDraw, ImageFont
from flask import Flask, request, redirect, url_for, render_template
from flask_uploads import UploadSet, IMAGES, configure_uploads
from train_model import Model
app = Flask(__name__)# 配置 Flask 文件上传# 注意这里的配置名称与上传集 'photos' 的名称一致
app.config['UPLOADED_PHOTOS_DEST']= os.path.join(os.path.dirname(os.path.abspath(__file__)),'uploads')
app.config['UPLOADED_PHOTOS_ALLOW']= IMAGES
photos = UploadSet('photos', IMAGES)
configure_uploads(app, photos)# 人脸识别的标签(名字列表)
new_names =["张国荣","王祖贤","彭于晏","特狼普","章子怡"]# 加载人脸检测模型
face_cascade = cv2.CascadeClassifier('config/haarcascade_frontalface_alt.xml')# 解决cv2.putText绘制中文乱码的问题defcv2ImgAddText(img, text, left, top, textColor=(0,0,255), textSize=20):ifisinstance(img, np.ndarray):
img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img)
fontStyle = ImageFont.truetype(r"C:\WINDOWS\FONTS\MSYH.TTC", textSize, encoding="utf-8")
draw.text((left, top), text, textColor, font=fontStyle)return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)defdetectOnePicture(path):'''
单图识别
'''
model = Model()
model.load()# 读取图像并转换为灰度图
img = cv2.imread(path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 检测人脸
faces = face_cascade.detectMultiScale(
gray,
scaleFactor=1.15,# 调整比例因子
minNeighbors=5,# 保持默认值#minSize=(100, 100) # 设置较大的最小检测尺寸)iflen(faces)==0:return"抱歉,未检测到人脸!"for(x, y, w, h)in faces:
roi = gray[y:y + h, x:x + w]
roi = cv2.resize(roi,(128,128), interpolation=cv2.INTER_LINEAR)
label, prob = model.predict(roi)if prob >0.5:
show_name =f"{new_names[label]} ({prob:.2f})"
res =f"识别为: {new_names[label]} 的概率为: {prob:.2f}"else:
res ="抱歉,未识别出该人!请尝试增加数据量来训练模型!"
img = cv2ImgAddText(img, show_name, x +5, y -30)
cv2.rectangle(img,(x, y),(x + w, y + h),(255,0,0),2)
cv2.imwrite(path, img)print(res)return res
@app.route('/upload', methods=['POST','GET'])defupload():if request.method =='POST'and'photo'in request.files:
filename = photos.save(request.files['photo'])return redirect(url_for('show', name=filename))return render_template('upload.html')@app.route('/photo/<name>')defshow(name):ifnot name:print('出错了!')return redirect(url_for('upload'))
file_path = os.path.join(app.config['UPLOADED_PHOTOS_DEST'], name)ifnot os.path.exists(file_path):returnf"文件 {name} 不存在",404
start_time = time.time()
res = detectOnePicture(file_path)
end_time = time.time()
execute_time =round(end_time - start_time,2)
tsg =f'总耗时为: {execute_time} 秒'
url = photos.url(name)return render_template('show.html', url=url, name=name, xinxi=res, shijian=tsg)if __name__ =="__main__":ifnot os.path.exists(app.config['UPLOADED_PHOTOS_DEST']):
os.makedirs(app.config['UPLOADED_PHOTOS_DEST'])print('Face Recognition Demo')
app.run(debug=True)
pyqt5 搭建可视化界面,实现图片识别和摄像头识别
完整代码如下
注意注意注意:在代码中的 cap = cv2.VideoCapture(1) 需要改为 cap = cv2.VideoCapture(0),0代表本电脑自带摄像头,1代码其他外接摄像头,因为我用的外接摄像头所示写 1,大家没有的话改成 0:
import os
import sys
import cv2
import numpy
from PyQt5.QtWidgets import QApplication, QMainWindow, QLabel, QPushButton, QVBoxLayout, QWidget, QFileDialog
from PyQt5.QtGui import QPixmap, QImage
from PyQt5.QtCore import Qt
from PIL import Image, ImageDraw, ImageFont
from Demo import Camera_reader
from train_model import Model
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
os.environ['CUDA_VISIBLE_DEVICES']='0'# 解决cv2.putText绘制中文乱码defcv2ImgAddText(img2, text, left, top, textColor=(0,0,255), textSize=20):ifisinstance(img2, numpy.ndarray):
img2 = Image.fromarray(cv2.cvtColor(img2, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img2)
fontStyle = ImageFont.truetype(r"C:\WINDOWS\FONTS\MSYH.TTC", textSize, encoding="utf-8")
draw.text((left, top), text, textColor, font=fontStyle)return cv2.cvtColor(numpy.asarray(img2), cv2.COLOR_RGB2BGR)# 新的名字列表
new_names =["张国荣","王祖贤","彭于晏","特狼普","章子怡"]classFaceDetectionApp(QMainWindow):def__init__(self, parent=None):super().__init__(parent)
self.setWindowTitle("人脸检测应用")
self.setGeometry(100,100,800,600)
self.central_widget = QWidget()
self.setCentralWidget(self.central_widget)
self.layout = QVBoxLayout()
self.upload_button = QPushButton("图片识别")
self.upload_button.clicked.connect(self.upload_image)
self.upload_button.setFixedSize(779,50)
self.camera_button = QPushButton("摄像头识别")
self.camera_button.clicked.connect(self.start_camera_detection)
self.camera_button.setFixedSize(779,50)
self.image_label = QLabel()
self.image_label.setAlignment(Qt.AlignCenter)
self.image_label.setFixedSize(779,500)
self.result_label = QLabel("识别结果: ")
self.result_label.setAlignment(Qt.AlignCenter)
self.layout.addWidget(self.upload_button)
self.layout.addWidget(self.camera_button)
self.layout.addWidget(self.image_label)
self.layout.addWidget(self.result_label)
self.central_widget.setLayout(self.layout)
self.model = Model()
self.model.load()defupload_image(self):
options = QFileDialog.Options()
options |= QFileDialog.ReadOnly
file_name, _ = QFileDialog.getOpenFileName(self,"选择图片","","Images (*.png *.jpg *.jpeg *.bmp *.gif *.tiff)", options=options)if file_name:
image = cv2.imread(file_name)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
face_cascade = cv2.CascadeClassifier('config/haarcascade_frontalface_alt.xml')
faces =(face_cascade.detectMultiScale(
gray,
scaleFactor=1.15,# 较小的比例因子
minNeighbors=5,# 保持默认值#minSize=(100, 100) # 设置较大的最小检测尺寸)# (gray, 1.35, 5))iflen(faces)>0:for(x, y, w, h)in faces:
roi = gray[y:y + h, x:x + w]
roi = cv2.resize(roi,(128,128), interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(roi)if prob >0.5:
show_name = new_names[label]
res =f"识别为: {show_name}, 概率: {prob:.2f}"else:
show_name ="陌生人"
res ="抱歉,未识别出该人!请尝试增加数据量来训练模型!"
frame = cv2ImgAddText(image, show_name, x +5, y -30)
cv2.rectangle(frame,(x, y),(x + w, y + h),(255,0,0),2)
cv2.imwrite('prediction.jpg', frame)
self.result = cv2.cvtColor(frame, cv2.COLOR_BGR2BGRA)
self.QtImg = QImage(
self.result.data, self.result.shape[1], self.result.shape[0], QImage.Format_RGB32)
self.image_label.setPixmap(QPixmap.fromImage(self.QtImg))
self.image_label.setScaledContents(True)# 自适应界面大小
self.result_label.setText(res)else:
self.result_label.setText("未检测到人脸")defstart_camera_detection(self):
self.camera = Camera_reader()
self.camera.build_camera()classCamera_reader(object):def__init__(self):
self.model = Model()
self.model.load()
self.img_size =128defbuild_camera(self):
face_cascade = cv2.CascadeClassifier('config/haarcascade_frontalface_alt.xml')
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()while success and cv2.waitKey(1)==-1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces =(face_cascade.detectMultiScale(
gray,
scaleFactor=1.05,# 较小的比例因子
minNeighbors=5,# 保持默认值#minSize=(100, 100) # 设置较大的最小检测尺寸))for(x, y, w, h)in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI,(self.img_size, self.img_size), interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(ROI)if prob >0.7:
show_name = new_names[label]else:
show_name ="陌生人"
frame = cv2ImgAddText(frame, show_name, x +5, y -30)
frame = cv2.rectangle(frame,(x, y),(x + w, y + h),(255,0,0),2)
cv2.imshow("Camera", frame)else:
cameraCapture.release()
cv2.destroyAllWindows()if __name__ =="__main__":
app = QApplication(sys.argv)
window = FaceDetectionApp()
window.show()
sys.exit(app.exec_())
总结
完整源码+数据集+模型,地址: 源码下载
提取码: kagm
本文通过opencv+cnn网络模型结合实现人脸识别,opencv实现人脸识别,cnn实现人脸的特征提取,并识别是某个人,cnn模型有待优化,你们可以自己需求更换其它的深度学习模型,增加训练数据集样本,实现更精准的人脸识别模型,有问题评论区留言,谢谢观看
博主熬夜写博客写代码,已经掉一大把头发了,麻烦点个赞赞鼓励一下
版权归原作者 挂科边缘 所有, 如有侵权,请联系我们删除。