A Mathematical Toolkit to improve the Similarity Analysis for Fingerprint Images

• Elioenai M. F. Diniz UTFPR http://orcid.org/0009-0007-7889-0671
• João V. C. Mazzochin UTFPR https://orcid.org/0009-0006-4246-0015
• Luiz A. Zanlorensi Infant.ID https://orcid.org/0000-0003-2545-0588
• Wesley A. C. de Bona UTFPR https://orcid.org/0009-0008-6743-6892
• Luiz F. P. Southier UTFPR http://orcid.org/0000-0003-2420-4094
• Fábio Favarim UTFPR
• Dalcimar Casanova UTFPR https://orcid.org/0000-0002-1905-4602

DOI: https://doi.org/10.5753/wsis.2024.33664

Abstract

While fingerprint biometrics are a mature technology, preprocessing steps such as image alignment and minutiae filtering still significantly impact their performance. To address these challenges, this paper introduces a comprehensive package of analytical methods designed to enhance fingerprint image similarity analysis. Initially, we present an alignment method based on partitioning and statistical image analysis, which does not rely on specific information, such as the location of singular points. Next, a minutiae filtering method is developed, focusing on detecting and removing edge minutiae, which tend to provide non-discriminative information. To establish an agnostic distance metric approach, we conducted extensive experiments on public fingerprint datasets, incorporating an ablation study to evaluate the impact of alignment and filtering methods. Our results demonstrate that the proposed combination of rotation and filtering significantly outperforms untreated images, providing an efficient and competitive solution that improves and contributes to the biometric analysis field.

Keywords: Fingerprint, Similarity, Analytical, Comparative, Outperforming

References

D. Maltoni, ”A tutorial on fingerprint recognition,” in *Advanced Studies in Biometrics, Lecture Notes in Computer Science*, Springer Berlin Heidelberg, 2005, pp. 43-68

P. Schuch, J. M. May, and C. Busch, ”Unsupervised learning of fingerprint rotations,” in *Proc. 2018 Int. Conf. Biometrics Special Interest Group (BIOSIG)*, 2018, pp. 1-6, DOI: 10.23919/BIOSIG.2018.8553096.

T. Hotz, ”Intrinsic coordinates for fingerprints based on their longitudinal axis,” in *Proc. 6th Int. Symp. Image and Signal Processing and Analysis*, 2009, pp. 500-504, DOI: 10.1109/ISPA.2009.5297679.

X. Yang, J. Feng, and J. Zhou, ”Localized dictionaries based orientation field estimation for latent fingerprints,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. 36, no. 5, pp. 955-969, May 2014, DOI: 10.1109/TPAMI.2013.184.

P. Mansukhani *et al.*, ”Using support vector machines to eliminate false minutiae matches during fingerprint verification,” in *Proc. Salil Prabhakar and Arun A. Ross (Eds.),* 2007, p. 65390B. DOI: 10.1117/12.720769.

S. Jabeen and S. A. Khan, ”A hybrid false minutiae removal algorithm with boundary elimination,” in *Proc. 2008 IEEE Int. Conf. System of Systems Engineering*, 2008, pp. 1-6, DOI: 10.1109/SYSOSE.2008.4724177.

F. Abed and A. Maroof, ”Fingerprint image pre- and post-processing methods for minutiae extraction,” *AL-Rafidain J. Comput. Sci. Math.*, vol. 6, no. 1, pp. 97-110, Mar. 2009, DOI: 10.33899/csmj.2009.163768.

C. Arcelli and G. S. Di Baja, ”A width-independent fast thinning algorithm,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. PAMI-7, no. 4, pp. 463-474, Jul. 1985, DOI: 10.1109/TPAMI.1985.4767685.

L. Hong, Y. Wan, and A. Jain, ”Fingerprint image enhancement: algorithm and performance evaluation,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. 20, no. 8, pp. 777-789, Aug. 1998, DOI: 10.1109/34.709565.

S. Chavan, P. Mundada, and D. Pal, ”Fingerprint authentication using Gabor filter based matching algorithm,” in *Proc. 2015 Int. Conf. Technologies for Sustainable Development (ICTSD)*, 2015, pp. 1-6, DOI: 10.1109/ICTSD.2015.7095910.

Natosafe, ”Infant.ID - Born to be unique,” *Natosafe*, [Online]. Available: [link]. [Accessed: Jul. 6, 2024].

J. H. Wegstein, ”An automated fingerprint identification system,” *U.S. Government Publication*, 1982, DOI: 10.6028/nbs.sp.500-89. [Online]. Available: DOI: 10.6028/nbs.sp.500-89.

FVC-onGoing: Fingerprint Verification Competition*, Biometric System Laboratory - University of Bologna, [Online]. Available: [link]. [Accessed: Aug. 20, 2024].

L. Lam, S.-W. Lee, and C. Y. Suen, ”Thinning methodologies—a comprehensive survey,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. 14, no. 9, pp. 869-885, Sep. 1992, DOI: 10.1109/34.161346.

D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge, ”Comparing images using the Hausdorff distance,” *IEEE Trans. Pattern Anal. Mach. Intell.*, vol. 15, no. 9, pp. 850-863, Sep. 1993, DOI: 10.1109/34.232073.

O. Pele and M. Werman, ”Fast and robust earth mover’s distances,” in *Proc. 2009 IEEE 12th Int. Conf. Computer Vision*, Sep. 2009, pp. 460-467.

A. Bakshi, P. Indyk, R. Jayaram, S. Silwal, and E. Waingarten, ”A nearlinear time algorithm for the Chamfer distance,” *arXiv*, 2023. [Online]. Available: [link].

N. P. Jouppi, D. H. Yoon, G. Kurian, S. Li, N. Patil, J. Laudon, C. Young, and D. Patterson, ”A domain-specific supercomputer for training deep neural networks,” Commun. ACM, vol. 63, no. 7, pp. 67–78, Jul. 2020, DOI: 10.1145/3360307.

L. Bottou and C.-J. Lin, ”Support Vector Machine Solvers,” Large-Scale Kernel Machines, pp. 1-28, Aug. 2007. [Online]. DOI: 10.7551/mitpress/7496.003.0003.