使用TensorFlow深度学习实现人脸识别,使用网络摄像头作为Raspberry Pi上的监控摄像头,旨在为需求方提供安全感。一个频频出现的监控摄像机问题是,犯罪是在一定时间内进行的,缺乏预警特征,没有在监控摄像机上应用面部识别。本系统的功能是对摄像头捕获的每一个人脸进行人脸识别。使用梯度方向直方图( HOG )方法进行深度学习的提取过程。从相机输入的图像将经过灰度缩放过程,然后将其取提取值,用TensorFlow的深度学习框架进行分类。当面孔未被识别时,系统将发送通知。在对数据进行分析的基础上,得出结论：人脸识别的实现是在树莓派上使用Python编程语言,借助TensorFlow,使得样本的训练过程更快、更准确。它采用一个图形用户界面( GUI )作为主显示器,并使用Python设计器构建,使用电子邮件作为向用户发出初始警告的媒介,以及使用网络摄像头作为主摄像头捕捉图像。

The implementation of face recognition with TensorFlow deep learning uses the webcam as a surveillance camera on the Raspberry Pi, aiming to provide a sense of security to the requiring party. A frequent surveillance camera problem is that crimes are performed at certain hours, the absence of early warning features, and there is no application of facial recognition on surveillance cameras. The function of this system is to perform facial recognition on every face captured by the webcam. Use the Histogram of the Oriented Gradient (HOG) method for the extraction process of deep learning. The image that is input from the camera will undergo a gray scaling process, then it will be taken the extraction value and classified by deep learning framework with TensorFlow. The system will send notifications when faces are not recognized. Based on the analysis of the data is done, the conclusion that the implementation of face recognition is built on the Raspberry Pi using a Python programming language with the help of TensorFlow so that the training process of the sample is much faster and more accurate. It uses a Graphical User Interface (GUI) as the main display and is built using Python designer, using email as an initial warning delivery medium to the user as well as using the webcam as the main camera to capture image.