计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (16): 193-196.DOI: 10.3778/j.issn.1002-8331.2009.16.057

• 图形、图像、模式识别 • 上一篇    下一篇

姿态变化估计策略下的人脸真实性判别研究

任 勇1,张 楠2,牟轩沁2   

  1. 1.重庆大学 通信工程学院,重庆 400044
    2.西安交通大学 电信学院 图像处理与识别研究所,西安 710049
  • 收稿日期:2008-12-10 修回日期:2009-02-27 出版日期:2009-06-01 发布日期:2009-06-01
  • 通讯作者: 任 勇

Face liveness verification using estimation of face pose variation

REN Yong1,ZHANG Nan2,MOU Xuan-qin2   

  1. 1.College of Communication Engineering,Chongqing University,Chongqing 400044,China
    2.Institute of Image Processing and Pattern Recognition,Xi’an Jiaotong University,Xi’an 710049,China
  • Received:2008-12-10 Revised:2009-02-27 Online:2009-06-01 Published:2009-06-01
  • Contact: REN Yong

摘要: 针对人脸识别系统中的欺骗手段,提出了一种基于姿态变化的脸部真实性判别算法。在构建的真实性判别系统中,引入了新的脸部特征点匹配标准函数及变形块匹配方法,对脸部序列图像特征点对位置进行精确提取和进行运动估计,最终通过对脸部姿态变化的策略分析完成真实性判别。算法分析及实验结果表明,该算法特别对照片欺骗手段具有良好的防范作用,可以较好地加强人脸识别系统的安全性。

关键词: 人脸识别, 真实性判别, 人脸姿态, 块匹配, 运动估计

Abstract: Aiming at photo deception in face recognition system,a new face liveness verification algorithm using estimation of face pose variation is presented.A block match algorithm based on variable-block and the new matching criterion function were used to get accurate positions of facial feature points and motion estimation of facial feature points.The verification was achieved through analysis of pose variation and head movement.Algorithm analysis and experimental results show that the algorithm can distinguish live faces from attacks of still photoes ,and enhance the safety of the whole face recognition system.

Key words: face recognition, liveness verification, face pose, block match, motion estimation