信息网络安全

信息网络安全 ›› 2017, Vol. 17 ›› Issue (12): 80-84.doi: 10.3969/j.issn.1671-1122.2017.12.014

• • 上一篇    下一篇

面向人口信息人像比对应用的人像比对算法研究

康凯1(), 王重道2, 王生进3, 范英1   

  1. 1.公安部户政管理研究中心,北京 100070
    2.清华大学电子工程系,北京 100084
    3.清华大学智能技术与系统国家重点实验室,北京 100084
  • 收稿日期:2017-11-01 出版日期:2017-12-20 发布日期:2020-05-12
  • 作者简介:

    作者简介：康凯（1981—）,男,北京,助理研究员,硕士,主要研究方向为人口信息化;王重道（1994—）,男,北京,博士研究生,主要研究方向为智能技术;王生进（1962—）,男,北京,教授,博士,主要研究方向为智能技术;范英（1977—）,女,北京,副研究员,本科,主要研究方向为人口信息化。

Research of Face Verification Algorithms for Population Information Analysis Applications

Kai KANG1(), Zhongdao WANG2, Shengjin WANG3, Ying FAN4   

  1. 1.Research Center of Census Administration M.P.S.PRC, Beijing 100070, China
    2.Department of Electrical Engineering, Tsinghua University, Beijing 100084, China
    3. State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China
  • Received:2017-11-01 Online:2017-12-20 Published:2020-05-12

RichHTML

4

PDF (PC)

541

摘要：

随着社会各行业对有效的自动身份认证的迫切需求,生物特征识别技术在近几十年取得了飞速的发展。作为人的一种内在属性,人脸具有很强的自身稳定性和个体差异性,并且具有非强制性、非接触性和并发性等特点,成为了自动身份验证最理想的依据。因此人脸识别一直是模式识别领域的热点研究课题。文章首先对人像比对应用的研究背景和意义进行了简要介绍;然后介绍了面向人口信息人像比对应用的人像比对算法流程;其次针对人脸检测、人脸关键点定位和人脸识别这三项关键技术,分别介绍了三者的基本原理和处理流程、研究现状以及存在的问题;最后进行了总结。

关键词: 人像比对, 人脸检测, 人脸识别

Abstract:

With the significant increasing demand of automatic and high-accuracy identify verification technology from various sectors of society, many research have made great development on biometric identification technology in the last decades. As one kind of biometric feature, human faces have strong stability and identity-variance. Furthermore, face recognition has characters such as non-obligatory, non-contact and concurrency, which lead it to an ideal evidence to automatic identification. This paper briefly introduces the pipeline of face verification algorithms for applications on population information analysis, and then makes some research on the key points and key technologies respectively. Firstly this paper briefly introduces the background and significance of face verification applications. Secondly, with respect to three key technologies of face detection, face alignment and face recognition, this paper introduces the basic principles, process pipeline, research situation and existing problems, respectively, and finally gives a simple summary.

Key words: face verification, face detection, face recognition

中图分类号: