摘要
如何在有效的时间内准确地识别人脸信息成为目前需要研究的重要问题,笔者基于融合深度卷积神经网络对人脸识别方法进行研究,首先设计了基于融合深度卷积神经网络的人脸识别方法,即利用PCA算法提取人脸特征,然后激活神经网络函数,最后构建神经网络模型对单个深度卷积网络进行训练,从而实现人脸识别.实验结果表明:基于融合深度卷积神经网络的人脸识别方法优于其他方法,具有一定的扩展性.
How to accurately recognize face information within an effective time has become an important issue that needs to be studied at present,so based on the fusion of deep convolutional neural networks,the method of face recognition is studied.The research first designed a face recognition method based on the fusion of deep convolutional neural networks,that is,extracting facial features from the PCA algorithm,then activating the neural network function,building the neural network model,and then training a single deep convolutional network,thus Realize face recognition.The experimental results show that the proposed neural network face recognition method is superior to the method and has a certain scalability.
作者
褚玉晓
CHU Yuxiao(School of Electronics and Information Engineering,SIAS University,Zhengzhou Henan 451150,China)
出处
《信息与电脑》
2021年第10期173-175,共3页
Information & Computer
基金
河南省高等学校重点科研项目(项目编号:19B520027)。
关键词
融合深度卷积
人脸识别
神经网络
PCA算法
fusion deep convolution
face recognition
neural networks
PCA algorithm
