《电子技术应用》
您所在的位置:首页 > 人工智能 > 设计应用 > 基于Wi-Fi和人脸识别技术的智能锁系统设计
基于Wi-Fi和人脸识别技术的智能锁系统设计
2021年电子技术应用第6期
周 扬,熊俊俏
武汉工程大学 电气信息学院,湖北 武汉430205
摘要: 针对传统门锁存在的安全问题,设计了一款将Wi-Fi技术与人脸识别技术相结合的智能锁系统。该系统采用STM32F103作为核心控制器件,CC1101作为通信传输模块,有效降低功耗的同时实现了信息的交互。同时提出MULBP人脸识别算法,相较于改进前增强了图像灰度均值与每行、每列以及对角线元素的关系,得到的全新LBP算子值更能够反映出局部纹理特征,再与2DLDA算法相结合找到投影矩阵,使样本更容易被区分,更便于特征提取。结果表明,这种融合算法在降低特征维数的同时也提高了识别率,使得系统达到了智能防盗的目的。
中图分类号: TN929.5;TP391.4
文献标识码: A
DOI:10.16157/j.issn.0258-7998.200861
中文引用格式: 周扬,熊俊俏. 基于Wi-Fi和人脸识别技术的智能锁系统设计[J].电子技术应用,2021,47(6):57-61.
英文引用格式: Zhou Yang,Xiong Junqiao. Design of intelligent lock system based on Wi-Fi and face recognition technology[J]. Application of Electronic Technique,2021,47(6):57-61.
Design of intelligent lock system based on Wi-Fi and face recognition technology
Zhou Yang,Xiong Junqiao
School of Electrical and Information Engineering,Wuhan Institute of Technology,Wuhan 430205,China
Abstract: Aiming at the security problems existing in traditional door locks, an intelligent lock system combining Wi-Fi technology and face recognition technology is designed. The system adopts STM32F103 as the core control device and CC1101 as the communication and transmission module, which can effectively reduce power consumption and realize information interaction. MULBP(Multiple Uniform Local Binary Patterns,MULBP) face recognition algorithm is put forward at the same time, compared with before improvement to enhance the image grayscale average and each row, column and diagonal elements, the relationship between value of new LBP operator is more able to reflect the local texture feature, and combined with 2DLDA(Two-dimensional Linear Discriminant Analysis,2DLDA) algorithm find the projection matrix, to make the sample more easy to distinguish, easier for feature extraction. The results show that the fusion algorithm not only reduces the feature dimension but also improves the recognition rate, making the system achieve the purpose of intelligent anti-theft.
Key words : intelligent lock;wireless communication technology;local binary mode;two-dimensional linear discriminant analysis

0 引言

    随着无线通信技术和物联网技术的不断发展,人们的财产安全和信息安全意识不断提升,智能家居的理念也已经成为人们关注的热点问题[1-2]。文献[3]中介绍的智能锁系统采用了一种蓝牙与FPGA相结合的技术,经验证表明该系统的保密性和安全性都有所增强,但存在功耗较大和成本较高的问题;文献[4]中提出了一种基于LBP特征和改进Fisher准则的方法来提取直方图的特征,得到了较好的效果,但忽略了人脸的局部细微特征。因此,本文采用传输速度快、接入方便的Wi-Fi技术来完成智能锁的通信,选择功耗较低且频段丰富的CC1101芯片来完成数据的收发。并结合多重均匀局部二值模式(Multiple Uniform Local Binary Patterns,MULBP)与二维线性判别分析(Two-dimensional Linear Discriminant Analysis,2DLDA)融合人脸识别算法采集信息进行身份识别,经实测表明该系统实现数据稳定传输的同时略微提升了识别的准确率。




本文详细内容请下载:http://www.chinaaet.com/resource/share/2000003574




作者信息:

周  扬,熊俊俏

(武汉工程大学 电气信息学院,湖北 武汉430205)




wd.jpg

此内容为AET网站原创,未经授权禁止转载。