A Novel Fast Fingerprint Matching Method Based on Feature Descriptors

In order to improve the fingerprint unlocking speed of smart phones, this paper proposes a fingerprint fast matching algorithm which is Ultrashort binary descriptor-Phase-Only Correlation (USB-POC). The algorithm has the advantages of fast match speed of the Ultrashort binary descriptor (USB) descriptor and high accuracy of Phase-Only Correlation (POC) algorithm. The experimental result shows the USB-POC algorithm can achieve fast and accurate fingerprint matching in many templates, meanwhile, the fingerprint unlocking speed is significantly improved.

[1]  Tsuyoshi Isshiki,et al.  Fingerprint authentication on touch sensor using Phase-Only Correlation method , 2016, 2016 7th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES).

[2]  Shreyasi Das,et al.  Methodology for partial fingerprint enrollment and authentication on mobile devices , 2016, 2016 International Conference on Biometrics (ICB).

[3]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[4]  Fanglin Chen,et al.  On the Influence of Fingerprint Area in Partial Fingerprint Recognition , 2012, CCBR.

[5]  Fanglin Chen,et al.  A Fusion Method for Partial Fingerprint Recognition , 2013, Int. J. Pattern Recognit. Artif. Intell..

[6]  Judith Liu-Jimenez,et al.  Small fingerprint scanners used in mobile devices: the impact on biometric performance , 2016, IET Biom..

[7]  Raul Sánchez-Reillo,et al.  Strengths, weaknesses and recommendations in implementing biometrics in mobile devices , 2014, 2014 International Carnahan Conference on Security Technology (ICCST).

[8]  Shiliang Zhang,et al.  USB: Ultrashort Binary Descriptor for Fast Visual Matching and Retrieval , 2014, IEEE Transactions on Image Processing.