A multibiometric finger vein verification system based on score level fusion strategy

Multibiometric systems are very applicable in human identification systems nowadays. However, using different biometrics may need extra acquisition sensors besides algorithm complexity. In this paper, a new multi-instance human identification system is proposed using different finger vein biometrics. In the proposed method, the multibiometric system is implemented using score level fusion. A complete investigation is done on effectiveness of different score level fusion strategies. For the proposed multi finger vein biometric system experimental results confirm that maximum score level fusion strategy outperforms other fusion methods in addition to some classical fusion algorithms in terms of EER.

[1]  Kang Ryoung Park,et al.  Multimodal biometric method based on vein and geometry of a single finger , 2010 .

[2]  B. Ton.  Vascular patern of the finger: biometric of the future? Sensor design, data collection and performance verification , 2012 .

[3]  Jianping Li,et al.  User identification based on finger-vein patterns for consumer electronics devices , 2010, IEEE Transactions on Consumer Electronics.

[4]  Madasu Hanmandlu,et al.  Score level fusion of multimodal biometrics using triangular norms , 2011, Pattern Recognit. Lett..

[5]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  David Zhang,et al.  Second-Level Partition for Estimating FAR Confidence Intervals in Biometric Systems , 2009, CAIP.

[7]  Sim Hiew Moi,et al.  Multimodal biometrics: Weighted score level fusion based on non-ideal iris and face images , 2014, Expert Syst. Appl..

[8]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Chuck Wilson.  Vein Pattern Recognition: A Privacy-Enhancing Biometric , 2010 .

[10]  Fariba Yousefi.  ANALYSIS OF METHODS FOR FINGER VEIN RECOGNITION , 2013 .

[11]  Yilong Yin,et al.  SDUMLA-HMT: A Multimodal Biometric Database , 2011, CCBR.

[12]  Chengbo Yu,et al.  Finger-Vein Verification Based on Multi-Features Fusion , 2013, Sensors.

[13]  Naoto Miura,et al.  Feature extraction of finger vein patterns based on iterative line tracking and its application to personal identification , 2004 .

[14]  Puneet Gupta,et al.  An accurate finger vein based verification system , 2015, Digit. Signal Process..

[15]  Ajay Kumar,et al.  Human Identification Using Finger Images , 2012, IEEE Transactions on Image Processing.

[16]  Raymond N. J. Veldhuis,et al.  A high quality finger vascular pattern dataset collected using a custom designed capturing device , 2013, 2013 International Conference on Biometrics (ICB).