基于深度学习卷积神经网络的民航旅客人脸智能识别方法  

Civil Aviation Passenger Face Intelligent Recognition Method Based on Deep Learning Convolutional Neural Network

作　　者：张宁[1] 梁有程[1] 顾倩[1] 胡洋 臧雪梅 ZHANG Ning;LIANG Youcheng;GU Qian;HU Yang;ZANG Xuemei(Airport Management College,Guangzhou Civil Aviation College,Guangzhou Guangdong 510280,China;School of Information Engineering,Guangzhou Panyu Polytechnic,Guangzhou Guangdong 511483,China)

机构地区：[1]广州民航职业技术学院航空港管理学院,广东广州510280 [2]广州番禺职业技术学院信息技术学院,广东广州511483

出　　处：《信息与电脑》2022年第18期162-164,共3页Information & Computer

基　　金：广东省教育厅科技创新项目(自然科学)“民航安检人工智能旅客身份识别技术创新研究”(项目编号:2021KTSCX193);广东省教育厅科研创新项目(自然科学)“基于超声波传感技术的安防系统模型分析及电路设计”(项目编号:2022GKTSCX004)。

摘　　要：在民航旅客人脸识别中,由于人脸特征提取差,导致识别准确率低,因此提出基于深度学习卷积神经网络的民航旅客人脸智能识别方法。首先,利用深度学习卷积神经网络检测人脸,获取人脸位置并标记关键特征点;其次,基于人脸姿态校正提取关键特征,利用三角对线理论融合人脸特征;最后,通过计算待检测图像与数据集中图像的余弦相似度,实现人脸智能识别。实验结果表明,该方法的识别准确率在92%以上,证明其具备可行性。In civil aviation passenger face recognition,due to the poor extraction of face features,the recognition accuracy is low.Therefore,an intelligent civil aviation passenger face recognition method based on deep learning Convolutional Neural Network is proposed.The deep learning Convolutional Neural Network is used to detect the face,obtain the position of the face and mark the key feature points,extract the key features based on the face pose correction,fuse the face features using the triangle alignment theory,and calculate the cosine similarity between the image to be detected and the image in the data set to realize the intelligent face recognition.The experimental results show that the recognition accuracy of this method is over 92%,which proves its feasibility.

关 键 词：卷积神经网络(CNN) 民航旅客 人脸智能识别 三角对线理论 深度学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]