《计算机应用研究》|Application Research of Computers

人脸识别活体检测研究方法综述

Survey on face anti-spoofing in face recognition

免费全文下载 (已被下载 次)  
获取PDF全文
作者 邓雄,王洪春,赵立军,吴至友,皮家甜
机构 1.重庆师范大学 a.数学科学学院;b.智慧金融与大数据分析重庆市重点实验室;c.计算机与信息科学学院,重庆 401331;2.马上消费金融股份有限公司,重庆 401331
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)09-003-2579-07
DOI 10.19734/j.issn.1001-3695.2019.03.0106
摘要 人脸识别具有广泛的应用,但容易受到伪造的欺骗人脸攻击而影响安全性,设计检测准确率高、泛化能力强、满足实时性需求的活体检测方法是目前的研究重点。将现有的人脸活体检测研究方法分为基于手工设计特征表达、基于深度学习和基于融合策略的方法,介绍每类方法所包含的典型算法的基本思想、实现步骤及优缺点。最后对已公开的人脸活体检测数据库进行整理说明,对人脸活体检测的发展趋势以及还需要进一步解决的问题进行综述,为今后人脸活体检测的研究提供了参考和借鉴。
关键词 人脸识别; 活体检测; 特征提取; 深度学习; 融合策略
基金项目 重庆市基础研究与前沿探索项目(cstc2018jcyjAX0470)
重庆市教委科技项目青年项目(KJQN201800521)
重庆师范大学人才引进项目(17XLB021)
本文URL http://www.arocmag.com/article/01-2020-09-003.html
英文标题 Survey on face anti-spoofing in face recognition
作者英文名 Deng Xiong, Wang Hongchun, Zhao Lijun, Wu Zhiyou, Pi Jiatian
机构英文名 1.a.School of Mathematical Sciences,b.Key Laboratory of Intelligent Finance & Large Data Analysis in Chongqing,c.College of Computer & Information Science,Chongqing Normal University,Chongqing 401331,China;2.Mashang Consumer Finance Co. ,Ltd. ,Chongqing 401331,China
英文摘要 Face recognition has a wide range of applications, but it is vulnerable to spoofing attacks that affect security. How to design a method with high detection accuracy, strong generalization ability, and satisfying real-time requirements is the focus of current research. This paper divided the existing methods of face anti-spoofing into methods based on hand-crafted descriptor, deep learning and fusion strategy, and introduced the basic ideas, implementation steps and advantages and disadvantages of typical algorithms. Finally, it collated and explained the published databases of face anti-spoofing, summarized the development trend of face anti-spoofing and the problems that still further needed to be solved, which could provide reference for the future research of face anti-spoofing.
英文关键词 face recognition; face anti-spoofing; feature extraction; deep learning; fusion strategy
参考文献 查看稿件参考文献
 
收稿日期 2019/3/22
修回日期 2019/5/17
页码 2579-2585
中图分类号 TP391.41
文献标志码 A