[1]吴继鹏,蔡国榕,陈水利,等.基于FSLBP特征的人脸活体检测方法[J].集美大学学报(自然科学版),2017,22(5):65-72.
　WU Jipeng,CAI Guorong,CHEN Shuili,et al.Face AntiSpoofing Based on FSLBP Features[J].Journal of Jimei University,2017,22(5):65-72.
点击复制

基于FSLBP特征的人脸活体检测方法(PDF)

分享到：

《集美大学学报（自然科学版）》[ISSN:1007-7405/CN:35-1186/N]

作者:: 吴继鹏1; 2; 蔡国榕1; 3; 陈水利1; 4; 吴云东1; 3; （1.厦门市无人机遥感应用工程技术研究中心，福建厦门 361021；2.集美大学理学院，福建厦门 361021； 3.集美大学计算机工程学院，福建厦门 361021；4.集美大学诚毅学院，福建厦门 361021）

Author(s):: WU Jipeng1; 2; CAI Guorong1; 3; CHEN Shuili1; 4; WU Yundong1; 3; (1.Xiamen Unmanned Aerial Vehicle Remote Sensing Application Engineering Technology Research Center,Xiamen 361021,China;2.School of Science,Jimei University,Xiamen 361021,China;3.School of Computer Engineering,Jimei University,Xiamen 361021,China;4.Chengyi University College,Jimei University,Xiamen 361021,China)

Keywords:: face recognition; Fourier spectrum; local binary pattern; GLCM; anti; ; ; spoofing

摘要:: 针对人脸识别系统无法识别人脸图像是否来自真人的问题，首先改进了傅里叶频谱(Fourier spectrum，FS)特征的人脸活体检测方法，并验证了局部二值模式(local binary pattern,LBP)特征和灰度共生矩阵（graylevel cooccurrence matrix,GLCM）特征人脸活体检测性能。在此基础上，提出了融合LBP特征的FSLBP特征人脸活体检测算法。实验结果表明，提出的FSLBP特征在多数据库的混合数据的准确率高达83.17%，更优于多尺度局部二值模式（multiscale local binary pattern,MSLBP）特征。

Abstract:: For the face recognition system,it is difficult to recognize whether the human face image comes from a real person.Firstly,FS feature method was improved,and LBP feature method and GLCM feature method for face antispoofing were discussed respectively.Furthermore,two feature fusion techniques were presented based on FS feature and LBP feature,that is FSLBP method.Experimental results showed that the accuracy of FSLBP proposed in this paper is 83.17% higher than that of MSLBP.

[1]陈培芝,陈水利,陈国龙.Gabor小波和局部二值模式结合的一种人脸识别算法[J].集美大学学报(自然科学版),2010,15(4):317.
[2]计蕾,付永钢.基于模块化2D-LDA的视频监控中的人脸识别算法[J].集美大学学报(自然科学版),2014,19(3):219.
　JI Lei,FU Yong-gang.Face Recognition Algorithm Based on Modular 2D-LDA in Video Monitoring[J].Journal of Jimei University,2014,19(5):219.

更新日期/Last Update: 2017-11-07