Fingerprint Synthesis: Search with 100 Million Prints

Evaluation of large-scale fingerprint search algorithms has been limited due to lack of publicly available datasets. To address this problem, we utilize a Generative Adversarial Network (GAN) to synthesize a fingerprint dataset consisting of 100 million fingerprint images. In contrast to existing fingerprint synthesis algorithms, we incorporate an identity loss which guides the generator to synthesize fingerprints corresponding to more distinct identities. The characteristics of our synthesized fingerprints are shown to be more similar to real fingerprints than existing meth- ods via eight different metrics (minutiae count - block and template, minutiae direction - block and template, minutiae convex hull area, minutiae spatial distribution, block minutiae quality distribution, and NFIQ 2.0 scores). Additionally, the synthetic fingerprints based on our approach are shown to be more distinct than synthetic fingerprints based on published methods through search results and imposter distribution statistics. Finally, we report for the first time in open literature, search accuracy against a gallery of 1 00 million fingerprints (NIST SD4 Rank-1 accuracy of 89.7%).

[1]  Davide Maltoni,et al.  Fingerprint Indexing Based on Minutia Cylinder-Code , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Anil K. Jain,et al.  Learning a Fixed-Length Fingerprint Representation , 2019, IEEE transactions on pattern analysis and machine intelligence.

[3]  Anil K. Jain,et al.  Matching Fingerphotos to Slap Fingerprint Images , 2018, ArXiv.

[4]  Shervin Minaee,et al.  Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN , 2018, ArXiv.

[5]  Dario Maio,et al.  Synthetic fingerprint-database generation , 2002, Object recognition supported by user interaction for service robots.

[6]  Jin He,et al.  SVM-Based Synthetic Fingerprint Discrimination Algorithm and Quantitative Optimization Strategy , 2014, PloS one.

[7]  Jürgen Schmidhuber,et al.  Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction , 2011, ICANN.

[8]  M. Sadegh Riazi,et al.  SynFi: Automatic Synthetic Fingerprint Generation , 2020, IACR Cryptol. ePrint Arch..

[9]  Jianjiang Feng,et al.  Fingerprint indexing with pose constraint , 2016, Pattern Recognit..

[10]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Barry G. Sherlock,et al.  A model for interpreting fingerprint topology , 1993, Pattern Recognit..

[12]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[13]  F. Massey.  The Kolmogorov-Smirnov Test for Goodness of Fit , 1951 .

[14]  Stephanie Schuckers,et al.  Texture Modeling for Synthetic Fingerprint Generation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Sistema político,et al.  Unique Identification Authority of India , 2011 .

[16]  D. Sagi,et al.  Gabor filters as texture discriminator , 1989, Biological Cybernetics.

[17]  Robert S. Germain,et al.  Fingerprint matching using transformation parameter clustering , 1997 .

[18]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[19]  Anil K. Jain,et al.  Fingerprint Synthesis: Evaluating Fingerprint Search at Scale , 2018, 2018 International Conference on Biometrics (ICB).

[20]  Saeid Nahavandi,et al.  Fingerprint Synthesis Via Latent Space Representation , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[21]  Julian Togelius,et al.  DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution* , 2017, 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[22]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[23]  Kieran G Larkin,et al.  A coherent framework for fingerprint analysis: are fingerprints Holograms? , 2007, Optics express.

[24]  Anil K. Jain,et al.  Beyond Minutiae: A Fingerprint Individuality Model with Pattern, Ridge and Pore Features , 2009, ICB.

[25]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[26]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[27]  Bir Bhanu,et al.  Fingerprint Indexing Based on Novel Features of Minutiae Triplets , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Anil K. Jain,et al.  Longitudinal study of fingerprint recognition , 2015, Proceedings of the National Academy of Sciences.

[30]  Qijun Zhao,et al.  Fingerprint image synthesis based on statistical feature models , 2012, 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[31]  Carsten Gottschlich,et al.  Separating the real from the synthetic: minutiae histograms as fingerprints of fingerprints , 2013, IET Biom..

[32]  Anil K. Jain,et al.  Fingerprint indexing and matching: An integrated approach , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[33]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[34]  Nehemiah Grew,et al.  The description and use of the pores in the skin of the bands and feet, by the learned and ingenious Nehemiah Grew, M. D. Fellow of the College of physicians and of the Royal Society , 1684, Philosophical Transactions of the Royal Society of London.

[35]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[36]  Sharath Pankanti,et al.  On the individuality fingerprints , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.