Face Liveness Detection Using Dynamic Local Ternary Pattern (DLTP)

被引:26
作者
Parveen, Sajida [1 ,3 ]
Ahmad, Sharifah Mumtazah Syed [1 ,2 ]
Abbas, Nidaa Hasan [1 ]
Adnan, Wan Azizun Wan [1 ]
Hanafi, Marsyita [1 ,2 ]
Naeem, Nadeem [1 ,3 ]
机构
[1] Univ Putra Malaysia, Fac Engn, Dept Comp & Commun Syst Engn, Upm Serdang 43400, Selangor, Malaysia
[2] Res Ctr Excellence Wireless & Photon Network, Serdang 43400, Malaysia
[3] Quaid E Awam Univ Engn Sci & Technol, Fac Elect Elect & Comp Syst Engn, Nawabshah 67450, Pakistan
关键词
face liveness detection; dynamic local ternary pattern (DLTP); skin texture analysis;
D O I
10.3390/computers5020010
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Face spoofing is considered to be one of the prominent threats to face recognition systems. However, in order to improve the security measures of such biometric systems against deliberate spoof attacks, liveness detection has received significant recent attention from researchers. For this purpose, analysis of facial skin texture properties becomes more popular because of its limited resource requirement and lower processing cost. The traditional method of skin analysis for liveness detection was to use Local Binary Pattern (LBP) and its variants. LBP descriptors are effective, but they may exhibit certain limitations in near uniform patterns. Thus, in this paper, we demonstrate the effectiveness of Local Ternary Pattern (LTP) as an alternative to LBP. In addition, we adopted Dynamic Local Ternary Pattern (DLTP), which eliminates the manual threshold setting in LTP by using Weber's law. The proposed method was tested rigorously on four facial spoof databases: three are public domain databases and the other is the Universiti Putra Malaysia (UPM) face spoof database, which was compiled through this study. The results obtained from the proposed DLTP texture descriptor attained optimum accuracy and clearly outperformed the reported LBP and LTP texture descriptors.
引用
收藏
页数:15
相关论文
共 31 条
[1]  
Anjos A, 2014, ADV COMPUT VIS PATT, P65, DOI 10.1007/978-1-4471-6524-8_4
[2]   Face Spoofing Detection Based on Multiple Descriptor Fusion Using Multiscale Dynamic Binarized Statistical Image Features [J].
Arashloo, Shervin Rahimzadeh ;
Kittler, Josef ;
Christmas, William .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2015, 10 (11) :2396-2407
[3]   Texture classification via extended local graph structure [J].
Bashier, Housam Khalifa ;
Hoe, Lau Siong ;
Hui, Liew Tze ;
Azli, Mohd Fikri ;
Han, Pang Ying ;
Kwee, Wee Kouk ;
Sayeed, Md Shohel .
OPTIK, 2016, 127 (02) :638-643
[4]  
Chingovska I, 2013, INT CONF BIOMETR
[5]  
Chingovska I., 2016, FACE RECOGNITION SYS, P165, DOI DOI 10.1007/978-3-319-28501-6_8
[6]  
Chingovska I., 2012, BIOSIG, P1
[7]  
de Freitas Pereira Tiago, 2013, Computer Vision - ACCV 2012 Workshops. ACCV 2012 International Workshops. Revised Selected Papers, P121, DOI 10.1007/978-3-642-37410-4_11
[8]   An Automated System for Garment Texture Design Class Identification [J].
Dey, Emon Kumar ;
Tawhid, Md. Nurul Ahad ;
Shoyaib, Mohammad .
COMPUTERS, 2015, 4 (03) :265-282
[9]   Face Anti-Spoofing Based on General Image Quality Assessment [J].
Galbally, Javier ;
Marcel, Sebastien .
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, :1173-1178
[10]   An Investigation of Local Descriptors for Biometric Spoofing Detection [J].
Gragnaniello, Diego ;
Poggi, Giovanni ;
Sansone, Carlo ;
Verdoliva, Luisa .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2015, 10 (04) :849-863