人脸识别技术与考勤系统应用研究

发布时间：2018-10-10 08:01

【摘要】：随着科技的发展,智能化的考勤系统在企业、学校、事业单位等场所越来越多的被使用,尤其是基于生物识别方式的考勤系统更是成为研究的热点。在生物识别方式中,人脸识别是一种方便快捷、安全准确、用户友好的识别方式。本文在分析总结人脸识别相关方法的基础上,针对江苏省物联网技术与应用协同创新中心的考勤需求,设计出了一套基于人脸识别的考勤系统。首先,本文介绍了人脸识别的基本原理和主要的人脸检测及人脸识别方法,并针对本文设计的考勤系统的需求选择合适的方法。然后,为了提高人脸识别的精度,充分利用奇异值分解得到的奇异值向量特征和正交矩阵特征,本文提出一种基于奇异值向量识别与矩阵相似度判别相结合的两步人脸识别方法。利用ORL人脸数据库验证本文方法的有效性,实验结果显示,本文提出的方法相比传统方法在识别率上有明显的改进,具有很大的使用价值。最后,将基于奇异值分解的两步人脸识别方法应用到考勤系统中,分析考勤系统的需求,利用SQL Server 2008、Microsoft Visual Studio 2010和OpenCV2.4.10等工具,完成了数据库的设计和考勤系统的各个功能模块的实现,并对系统进行了功能测试和性能测试。测试结果表明,本文设计的考勤系统具有较好的人脸识别效果和考勤管理功能,符合需求分析的要求,具有一定的使用价值。
[Abstract]:With the development of science and technology, intelligent attendance system is more and more used in enterprises, schools, institutions and other places, especially the attendance system based on biometric identification has become a research hotspot. In biometric recognition, face recognition is a convenient, fast, safe and accurate, user-friendly recognition method. On the basis of analyzing and summarizing the related methods of face recognition, a set of attendance system based on face recognition is designed to meet the attendance requirements of Jiangsu Provincial Internet of things Technology and Application Collaborative Innovation Center. Firstly, this paper introduces the basic principle of face recognition and the main methods of face detection and face recognition, and selects the appropriate method according to the requirements of the attendance system designed in this paper. Then, in order to improve the accuracy of face recognition, the singular value vector feature and orthogonal matrix feature obtained by singular value decomposition are fully utilized. In this paper, a two-step face recognition method based on singular value vector recognition and matrix similarity discrimination is proposed. The ORL face database is used to verify the effectiveness of the proposed method. The experimental results show that the method proposed in this paper has a significant improvement in recognition rate compared with the traditional method, and has a great value in use. Finally, the two-step face recognition method based on singular value decomposition is applied to the attendance system. The requirements of the attendance system are analyzed, and the tools such as SQL Server 2008, Microsoft Visual Studio 2010 and OpenCV2.4.10 are used. The design of the database and the realization of each function module of the attendance system are completed, and the function test and the performance test of the system are carried out. The test results show that the attendance system designed in this paper has better face recognition effect and attendance management function, meets the requirements of demand analysis, and has certain use value.
【学位授予单位】：南京邮电大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP391.41

【参考文献】