SCIENTIA SINICA Informationis, Volume 49, Issue 1: 42-56(2019) https://doi.org/10.1360/N112018-00018

A fingerprint-template-generating method based on the 3D mapping of local minutiae

More info
  • ReceivedJan 18, 2018
  • AcceptedApr 20, 2018
  • PublishedJan 8, 2019


To enhance the security and irreversibility performance of the fingerprint template, a fingerprint-template-generating method is proposed based on the 3D mapping of local minutiae. First, we extract fingerprint minutiae features after preprocessing the fingerprint image and select the minutiae using parameter adaptive circular areas. Second, we project the minutiae into a line. Subsequently, quantization, mapping, and modulo operation are performed on the projected vectors to generate a fixed-length binary bit string. Finally, a fingerprint template is generated by combining the user's PIN code with a binary bit string. The experiments performed on FVC2002-DB1 and DB2 show that this template has advantages over the traditional ones in terms of recognition, revocation, non-invertibility, and performance.

Funded by




[1] Nagar A. Biometric template security. Eurasip J Adv Signal Process, 2008, 2008: 1--17. Google Scholar

[2] Rane S, Wang Y, Draper S C, et al. Secure biometrics: concepts, authentication architectures, and challenges. IEEE Signal Process Mag, 2013, 30: 51--64. Google Scholar

[3] Patel V M, Ratha N K, Chellappa R. Cancelable Biometrics: A review. IEEE Signal Process Mag, 2015, 32: 54-65 CrossRef ADS Google Scholar

[4] Kaur G, Singh G, Kumar V. A review on biometric recognition. Int J Bio-Sci Bio-Technol, 2014, 6: 69--76. Google Scholar

[5] Teoh A B J, Ling D N C, Goh A. Biohashing: two factor authentication featuring fingerprint data and tokenised random number. Pattern Recognition, 2004, 37: 2245-2255 CrossRef Google Scholar

[6] Kong A, Cheung K H, Zhang D. An analysis of BioHashing and its variants. Pattern Recognition, 2006, 39: 1359-1368 CrossRef Google Scholar

[7] Nanni L, Lumini A. Empirical tests on BioHashing. Neurocomputing, 2006, 69: 2390-2395 CrossRef Google Scholar

[8] Ratha N K, Chikkerur S, Connell J H. Generating cancelable fingerprint templates.. IEEE Trans Pattern Anal Mach Intell, 2007, 29: 561-572 CrossRef PubMed Google Scholar

[9] Feng Q, Su F, Cai A N, et al. Cracking cancelable fingerprint template of ratha. In: Proceedings of IEEE International Symposium on Computer Science and Computational Technology, 2008. 572--575. Google Scholar

[10] Tulyakov S, Farooq F, Mansukhani P. Symmetric hash functions for secure fingerprint biometric systems. Pattern Recognition Lett, 2007, 28: 2427-2436 CrossRef Google Scholar

[11] Ahmad T, Hu J K. Generating cancelable biometrie templates using a projection line. In: Proceedings of IEEE International Conference on Control Automation Robotics & Vision, 2011. 7--12. Google Scholar

[12] Chulhan Lee , Jeung-Yoon Choi , Kar-Ann Toh . Alignment-Free Cancelable Fingerprint Templates Based on Local Minutiae Information. IEEE Trans Syst Man Cybern B, 2007, 37: 980-992 CrossRef Google Scholar

[13] Lee C, Kim J. Cancelable fingerprint templates using minutiae-based bit-strings. J Network Comput Appl, 2010, 33: 236-246 CrossRef Google Scholar

[14] Ahmad T, Hu J K, Wang S. String-based cancelable fingerprint templates. In: Proceedings of IEEE International Conference on Industrial Electronics and Applications, 2011. 1028--1033. Google Scholar

[15] Jin Z, Jin Teoh A B, Ong T S. Fingerprint template protection with minutiae-based bit-string for security and privacy preserving. Expert Syst Appl, 2012, 39: 6157-6167 CrossRef Google Scholar

[16] Cappelli R, Ferrara M, Maltoni D. Minutia Cylinder-Code: a new representation and matching technique for fingerprint recognition.. IEEE Trans Pattern Anal Mach Intell, 2010, 32: 2128-2141 CrossRef PubMed Google Scholar

[17] Ferrara M, Maltoni D, Cappelli R. Noninvertible Minutia Cylinder-Code Representation. IEEE TransInformForensic Secur, 2012, 7: 1727-1737 CrossRef Google Scholar

[18] Wang S, Hu J. Alignment-free cancelable fingerprint template design: A densely infinite-to-one mapping (DITOM) approach. Pattern Recognition, 2012, 45: 4129-4137 CrossRef Google Scholar

[19] Wang S, Hu J. Design of alignment-free cancelable fingerprint templates via curtailed circular convolution. Pattern Recognition, 2014, 47: 1321-1329 CrossRef Google Scholar

[20] Li S, Kot A C. Fingerprint Combination for Privacy Protection. IEEE TransInformForensic Secur, 2013, 8: 350-360 CrossRef Google Scholar

[21] Moujahdi C, Bebis G, Ghouzali S. Fingerprint shell: Secure representation of fingerprint template. Pattern Recognition Lett, 2014, 45: 189-196 CrossRef Google Scholar

[22] Sandhya M, Prasad M V N K. K-nearest neighborhood structure (k-NNS) based alignment-free method for fingerprint template protection. In: Proceedings of IEEE International Conference on Biometrics, 2015. 386--393. Google Scholar

[23] Pambudi D S, Ahmad T, Usagawa T. Improving the performance of projection-based cancelable fingerprint template method. In: Proceedings of IEEE International Conference on Soft Computing and Pattern Recognition, 2016. 84--88. Google Scholar

[24] Wang S, Hu J. A blind system identification approach to cancelable fingerprint templates. Pattern Recognition, 2016, 54: 14-22 CrossRef Google Scholar

[25] Wang S, Deng G, Hu J. A partial Hadamard transform approach to the design of cancelable fingerprint templates containing binary biometric representations. Pattern Recognition, 2017, 61: 447-458 CrossRef Google Scholar

[26] Wang S, Yang W, Hu J. Design of Alignment-Free Cancelable Fingerprint Templates with Zoned Minutia Pairs. Pattern Recognition, 2017, 66: 295-301 CrossRef Google Scholar

[27] Adámek M, Matysek M, Neumann P. Security of Biometric Systems. Procedia Eng, 2015, 100: 169-176 CrossRef Google Scholar

[28] Xu Q W, Zhang X F. Generating cancelable fingerprint templates using minutiae local information. Acta Automat Sin, 2017, 43: 645--652. Google Scholar

[29] Das P, Karthik K, Chandra Garai B. A robust alignment-free fingerprint hashing algorithm based on minimum distance graphs. Pattern Recognition, 2012, 45: 3373-3388 CrossRef Google Scholar

[30] Jin Z, Lim M H, Teoh A B J. A non-invertible Randomized Graph-based Hamming Embedding for generating cancelable fingerprint template. Pattern Recognition Lett, 2014, 42: 137-147 CrossRef Google Scholar

  • Figure 1

    (Color online) The three-dimensional mapping of minutiae

  • Figure 2

    Process diagram of proposed method for fingerprint template generation

  • Figure 3

    (Color online) Parameter adaptive circular areas

  • Figure 4

    (Color online) The distance and angle formed by minutiae pair $(m_{j},m_{i})$

  • Figure 5

    (Color online) Features of projected minutiae

  • Figure 6

    (Color online) Three-dimensional array with cell size $\sigma_{L},~\sigma_{\gamma},~\sigma_{\phi}$

  • Figure 7

    (Color online) Genuine and imposter distributions in the safe-PIN scenario (with different keys). (a) FVC2002-DB1; (b) FVC2002-DB2

  • Figure 8

    (Color online) Genuine and imposter distributions in the stolen-PIN scenario (with the same key). (a) FVC2002-DB1; (b) FVC2002-DB2

  • Figure 9

    (Color online) FRR/FAR of FVC2002-DB1 and -DB2 in the stolen-PIN scenario. (a) FVC2002-DB1;protectłinebreak (b) FVC2002-DB2

  • Figure 10

    (Color online) ROC curves of Wang's method and proposed method in the stolen-PIN scenario

  • Figure 11

    (Color online) Pseudo-imposter and imposter (with different key) distributions for FVC2002-DB1 and -DB2. (a) FVC2002-DB1; (b) FVC2002-DB2

  • Table 1   Information about the databases used in our experiments
    Characteristics FVC2002-DB1 FVC2002-DB2
    Sensor Identix TouchView$\amalg$ (optical) Biometrika FX2000 (optical)
    Number of fingers 100 100
    Number of image per finger 8 8
    Resolution 500 dpi 569 dpi
    Image size 388 $\times$ 374 296$\times$560
    Quality Good Medium
  • Table 2   Parameter settings in the experiments
    Parameter Description Value range
    $\rho_{1},\rho_{2}$ The slopes of $y_{1},y_{2}$ $[-5,5]$
    $~c_{1},c_{2}~$ The $y$-intercepts of $y_{1},y_{2}$ $\{~-10,-9,\ldots,~10~\}$
    $~c_{L},c_{\gamma}$ The length and width of the cell $\{~15,16,\ldots,~30~\}$
    $~c_{\phi}~$ The height of the cell $\{~20,21,\ldots,~35~\}$
    $~G~$ The size of binary bit string $\{~200,250,\ldots,~3000~\}$
    $~P~$ The rows of pseudo-random matrix ($R$) $\{~300,400,\ldots,~2000~\}$
  • Table 3   EER of different parameters $(G,P)$
    $G$ $P$ FVC2002-DB1 FVC2002-DB2
    200 300 0.32 0.24
    1000 0.21 0.13
    1000 300 0.19 0.08
    1000 0.18 0.07
    1450 300 0.17 0.06
    1000 0.15 0.06
  • Table 4   EER comparison between the Wang's method and proposed method
    Methods Safe-PIN Stolen-PIN
    -DB1 (%) -DB2 (%) -DB1 (%) -DB2 (%)
    Wang et al. [26] 0 0 0.19 1
    Proposed method 0 0 0.1717 0.0606
  • Table 5   EER comparison under the stolen-PIN scenario
    Method FVC2002-DB1 FVC2002-DB2
    Lee and Kim [13] 10.30 9.50
    Jin et al. [15] 5.19 5.65
    Sandhya and Prasad [22] 4.71 3.44
    Das et al. [29] 2.27 3.79
    Jin et al. [30] 4.36 1.77
    Wang and Hu [19] 2 2.3
    Wang and Hu [24] 3 2
    Wang et al. [25] 1 2
    Proposed method 0.17 0.06

Copyright 2019 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有