Abstract: With the rapid growth in fingerprint databases, it has become necessary to develop excellent fingerprint indexing to achieve efficiency and accuracy. fingerprint indexing has been widely studied with real-valued features, but few studies focus on binary feature representation, which is more suitable to identify fingerprints efficiently in large-scale fingerprint databases. In this study, we propose a deep compact binary minutia cylinder code (DCBMCC) as an effective and discriminative feature representation for fingerprint indexing. Specifically, the minutia cylinder code (MCC), as the state-of-the-art fingerprint representation, is analyzed and its shortcomings are revealed. Accordingly, we propose a novel fingerprint indexing method based on deep neural networks to learn DCBMCC. Our novel network restricts the penultimate layer to directly output binary codes. Moreover, we incorporate independence, balance, quantization-loss-minimum, and similarity-preservation properties in this learning process. Eventually, a multi-index hashing (MIH) based fingerprint indexing scheme further speeds up the exact search in the Hamming space by building multiple hash tables on binary code substrings. Furthermore, numerous experiments on public databases show that the proposed approach is an outstanding fingerprint indexing method since it has an extremely small error rate with a very low penetration rate.

基于深度学习紧致二进制编码的指纹索引

[1]Bai C, Zhao T, Wang W, et al., 2015. An efficient indexing scheme based on K-plet representation for fingerprint database. Int Conf on Intelligent Computing, p.247-257.

[2]Bai C, Wang W, Zhao T, et al., 2016. Learning compact binary quantization of minutia cylinder code. Int Conf on Biometrics, p.1-6.

[3]Bhanu B, Tan X, 2003. Fingerprint indexing based on novel features of minutiae triplets. IEEE Trans Patt Anal Mach Intell, 25(5):616-622.

[4]Cappelli R, Ferrara M, Maltoni D, 2010. Minutia cylinder-code: a new representation and matching technique for fingerprint recognition. IEEE Trans Patt Anal Mach Intell, 32(12):2128-2141.

[5]Cappelli R, Ferrara M, Maltoni D, 2011. Fingerprint indexing based on minutia cylinder-code. IEEE Trans Patt Anal Mach Intell, 33(5):1051-1057.

[6]Do T, Doan A, Cheung N, 2016. Learning to hash with binary deep neural network. European Conf on Computer Vision, p.219-234.

[7]Ferrara M, Maltoni D, Cappelli R, 2012. Noninvertible minutia cylinder-code representation. IEEE Trans Inform Forens Secur, 7(6):1727-1737.

[8]Germain R, Califano A, Colville S, 1997. Fingerprint matching using transformation parameter clustering. IEEE Comput Sci Eng, 4(4):42-49.

[9]Gong Y, Lazebnik S, 2011. Iterative quantization: a procrustean approach to learning binary codes. IEEE Int Conf on Computer Vision and Pattern Recognition, p.817-824.

[10]Gong Y, Lazebnik S, Gordo A, et al., 2013. Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Patt Anal Mach Intell, 35:2916-2929.

[11]Heo J, Lee Y, He J, et al., 2012. Spherical hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.2957-2964.

[12]Heo J, Lee Y, He J, et al., 2015. Spherical hashing: binary code embedding with hyperspheres. IEEE Trans Patt Anal Mach Intell, 37(11):2304-2316.

[13]Iloanusi O, 2014. Fusion of finger types for fingerprint indexing using minutiae quadruplets. Patt Recogn Lett, 38:8-14.

[14]Iloanusi O, Gyaourova A, Ross A, 2011. Indexing fingerprints using minutiae quadruplets. IEEE Int Conf on Computer Vision and Pattern Recognition Workshops, p.127-133.

[15]Jiang X, Liu M, Kot A, 2006. Fingerprint retrieval for identification. IEEE Trans Inform Forens Secur, 1(4):532-542.

[16]Lee S, Kim Y, Park G, 2005. A feature map consisting of orientation and inter-ridge spacing for fingerprint retrieval. Int Conf on Audio- and Video-Based Biometric Person Authentication, p.184-190.

[17]Liang X, Asano T, Bishnu A, 2006. Distorted fingerprint indexing using minutia detail and Delaunay triangle. IEEE Int Symp on Voronoi Diagrams in Science and Engineering, p.217-223.

[18]Liang X, Bishnu A, Asano T, 2007. A robust fingerprint indexing scheme using minutia neighborhood structure and low-order Delaunay triangles. IEEE Trans Inform Forens Secur, 2(4):721-733.

[19]Liu M, Yap P, 2012. Invariant representation of orientation fields for fingerprint indexing. Patt Recogn, 45(7):2532-2542.

[20]Liu M, Jiang X, Kot A, 2007. Efficient fingerprint search based on database clustering. Patt Recogn, 40(6):1793-1803.

[21]Maltoni D, Maio D, Jain A, et al., 2009. Handbook of Fingerprint Recognition. Springer-Verlag, London, UK.

[22]Norouzi M, Punjani A, Fleet D, 2012. Fast search in hamming space with multi-index hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.3108-3115.

[23]Norouzi M, Punjani A, Fleet D, 2014. Fast exact search in hamming space with multi-index hashing. IEEE Trans Patt Anal Mach Intell, 36(6):1107-1119.

[24]Shen F, Shen C, Liu W, et al., 2015. Supervised discrete hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.37-45.

[25]Wang Y, Hu J, Phillips D, 2007. A fingerprint orientation model based on 2D Fourier expansion (FOMFE) and its application to singular-point detection and fingerprint indexing. IEEE Trans Patt Anal Mach Intell, 29(4):573-585.