基于人脸识别技术的图书馆门禁系统的研究  被引量:39

Study on library access control system based on face recognition technology

在线阅读下载全文

作  者:张静端[1] ZHANG Jingduan(Donghua University,Shanghai 200051,China)

机构地区:[1]东华大学,上海200051

出  处:《现代电子技术》2016年第18期99-103,共5页Modern Electronics Technique

基  金:国家自然科学基金资助项目(61274078)

摘  要:通过对人脸识别技术与其他身份识别技术的对比,分析不同技术之间的优缺点,进而提出基于人脸识别的图书馆门禁系统优于传统图书馆门禁系统,同时对系统的组成结构、工作原理、算法代码编写流程以及系统测试等进行了研究。传统图书馆门禁系统存在三个关键问题:存在不安全隐患、存在5%左右的误识率和识别速度慢。针对上述三个关键问题分别提出了解决方案。由于人脸识别技术有着"人脸无法替代"、非侵犯性的特性,因此将人脸识别技术应用于图书馆门禁系统,排除了传统图书馆门禁系统存在安全隐患的现象;从系统设备选型、网络设计、软件设计方面提升了人脸识别终端机对人脸的识别率;由于人脸的识别时间小于1 s,从根本上解决了图书馆门禁系统识别速度慢的问题。The facial recognition technology and other identification technologies are compared,and their advantages anddisadvantages are analyzed. And then it is proposed that the library access control system based on face recognition is superiorto the traditional library access control system. The composing structure and working principle of the system,code programmingprocess of the algorithm,and system testing for the library access control system are studied. There are three key problemsexisting in traditional library entrance guard system,such as potential safety hazard,about 5% false recognition rate,and slowidentification speed. The solutions to solve the above three key problems are proposed respectively. Since the face recognitiontechnology has the“irreplacable”and non?invasiveness characteristics,the face recognition technology is applied to the libraryaccess control system,so as to exclude the potential safety hazard existing in traditional library access control system. The facerecognition rate of the face recognition terminal was improved in the aspects of the system equipment selection,network designand software design. The face recognition time is less than one second,so the system can solve the low recognition speed of thelibrary access control system fundamentally.

关 键 词:人脸识别 人脸特征提取 图书馆门禁系统 局部保持投影算法 误识率 识别速度 

分 类 号:TN911.73.34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象