Semi-automatic fingerprint image restoration algorithm using a partial differential equation

Chaeyoung Lee; Sangkwon Kim; Soobin Kwak; Youngjin Hwang; Seokjun Ham; Seungyoon Kang; Junseok Kim; Chaeyoung Lee; Sangkwon Kim; Soobin Kwak; Youngjin Hwang; Seokjun Ham; Seungyoon Kang; Junseok Kim

doi:10.3934/math.20231408

AIMS Mathematics

2023, Volume 8, Issue 11: 27528-27541. doi: 10.3934/math.20231408

Previous Article Next Article

Research article

Semi-automatic fingerprint image restoration algorithm using a partial differential equation

1.
Department of Mathematics, Kyonggi University, Suwon 16227, Republic of Korea
2.
Department of Mathematics, Korea University, Seoul, 02841, Republic of Korea

Received: 25 July 2023 Revised: 18 September 2023 Accepted: 25 September 2023 Published: 27 September 2023
MSC : 65N06, 65D18, 68U10

A fingerprint is the unique, complex pattern of ridges and valleys on the surface of an individual's fingertip. Fingerprinting is one of the most popular and widely used biometric authentication methods for personal identification because of its reliability, acceptability, high level of security, and low cost. When using fingerprints as a biometric, restoring poor-quality or damaged fingerprints is an essential process for accurate verification. In this study, we present a semi-automatic fingerprint image restoration method using a partial differential equation to repair damaged fingerprint images. The proposed algorithm is based on the Cahn-Hilliard (CH) equation with a source term, which was developed for simulating pattern formation during the phase separation of diblock copolymers in chemical engineering applications. In previous work, in order to find an optimal model and numerical parameter values in the governing equation, we had to make several trial and error preliminary attempts. To overcome these problems, the proposed novel algorithm minimizes user input and automatically computes the necessary model and numerical parameter values of the governing equation. Computational simulations on various damaged fingerprint samples are presented to demonstrate the superior performance of the proposed method.
- automatic fingerprint restoration,
- diblock copolymer,
- the Cahn-Hilliard (CH) equation,
- phase-field model
Citation: Chaeyoung Lee, Sangkwon Kim, Soobin Kwak, Youngjin Hwang, Seokjun Ham, Seungyoon Kang, Junseok Kim. Semi-automatic fingerprint image restoration algorithm using a partial differential equation[J]. AIMS Mathematics, 2023, 8(11): 27528-27541. doi: 10.3934/math.20231408

Related Papers:

Abstract

A fingerprint is the unique, complex pattern of ridges and valleys on the surface of an individual's fingertip. Fingerprinting is one of the most popular and widely used biometric authentication methods for personal identification because of its reliability, acceptability, high level of security, and low cost. When using fingerprints as a biometric, restoring poor-quality or damaged fingerprints is an essential process for accurate verification. In this study, we present a semi-automatic fingerprint image restoration method using a partial differential equation to repair damaged fingerprint images. The proposed algorithm is based on the Cahn-Hilliard (CH) equation with a source term, which was developed for simulating pattern formation during the phase separation of diblock copolymers in chemical engineering applications. In previous work, in order to find an optimal model and numerical parameter values in the governing equation, we had to make several trial and error preliminary attempts. To overcome these problems, the proposed novel algorithm minimizes user input and automatically computes the necessary model and numerical parameter values of the governing equation. Computational simulations on various damaged fingerprint samples are presented to demonstrate the superior performance of the proposed method.

References

[1]	Biometric recognition: Challenges and opportunities, National Research Council, Whither Biometrics Committee, 2010. https://doi.org/10.17226/12720
[2]	Y. Wang, Z. Wu, J. Zhang, Damaged fingerprint classification by Deep Learning with fuzzy feature points, In: 2016 9th international congress on image and signal processing, BioMedical engineering and informatics (CISP-BMEI), IEEE, 2016,280–285. https://doi.org/10.1109/CISP-BMEI.2016.7852722
[3]	J. Bigun, E. Grosso, M. Tistarelli, Advanced studies in biometrics, Springer-Verlag Berlin/Heidelberg, 2005. https://doi.org/10.1007/b136906
[4]	M. Drahansky, M. Dolezel, J. Urbanek, E. Brezinova, T. H. Kim, Influence of skin diseases on fingerprint recognition, Biomed Res. Int., 2012 (2012), 626148. https://doi.org/10.1155/2012/626148 doi: 10.1155/2012/626148
[5]	J. K. Appati, P. K. Nartey, E. Owusu, I. W. Denwar, Implementation of a transform-minutiae fusion-based model for fingerprint recognition, Int. J. Math. Math. Sci., 2021 (2021), 5545488. https://doi.org/10.1155/2021/5545488 doi: 10.1155/2021/5545488
[6]	A. Halim, B. R. Kumar, An anisotropic PDE model for image inpainting, Comput. Math. Appl., 79 (2020), 2701–2721. https://doi.org/10.1016/j.camwa.2019.12.002 doi: 10.1016/j.camwa.2019.12.002
[7]	J. Yang, Z. Guo, D. Zhang, B. Wu, S. Du, An anisotropic diffusion system with nonlinear time-delay structure tensor for image enhancement and segmentation, Comput. Math. Appl., 107 (2022), 29–44. https://doi.org/10.1016/j.camwa.2021.12.005 doi: 10.1016/j.camwa.2021.12.005
[8]	H. Shams, T. Jan, A. A. Khalil, N. Ahmad, A. Munir, R. A. Khalil, Fingerprint image enhancement using multiple filters, PeerJ Comput. Sci., 9 (2023), e1183. https://doi.org/10.7717/peerj-cs.1183 doi: 10.7717/peerj-cs.1183
[9]	Y. Tu, Z. Yao, J. Xu, Y. Liu, Z. Zhang, Fingerprint restoration using cubic Bezier curve, BMC Bioinformatics, 21 (2020), 514. https://doi.org/10.1186/s12859-020-03857-z doi: 10.1186/s12859-020-03857-z
[10]	J. S. Bartunek, M. Nilsson, B. Sallberg, I. Claesson, Adaptive fingerprint image enhancement with emphasis on preprocessing of data, IEEE T. Image Process., 22 (2012), 644–656. https://doi.org/10.1109/TIP.2012.2220373 doi: 10.1109/TIP.2012.2220373
[11]	P. Sutthiwichaiporn, V. Areekul, Adaptive boosted spectral filtering for progressive fingerprint enhancement, Pattern Recognit., 46 (2013), 2465–2486. https://doi.org/10.1016/j.patcog.2013.02.002 doi: 10.1016/j.patcog.2013.02.002
[12]	I. Joshi, T. Prakash, B. S. Jaiswal, R. Kumar, A. Dantcheva, S. D. Roy, et al., Context-aware restoration of noisy fingerprints, IEEE Sens. Lett., 6 (2022), 1–4. https://doi.org/10.1109/LSENS.2022.3203787 doi: 10.1109/LSENS.2022.3203787
[13]	Q. Gao, P. Forster, K. R. Mobus, G. S. Moschytz, Fingerprint recognition using CNNs: Fingerprint preprocessing, In ISCAS 2001, The 2001 IEEE International Symposium on Circuits and Systems (Cat. No. 01CH37196), IEEE, 3 (2001), 433–436. https://doi.org/10.1109/ISCAS.2001.921340
[14]	J. Zhang, Z. Lu, M. Li, H. Wu, GAN-based image augmentation for finger-vein biometric recognition, IEEE Access, 7 (2019), 183118–183132. https://doi.org/10.1109/ACCESS.2019.2960411 doi: 10.1109/ACCESS.2019.2960411
[15]	I. Joshi, A. Utkarsh, P. Singh, A. Dantcheva, S. D. Roy, P. K. Kalra, On restoration of degraded fingerprints, Multimed. Tools Appl., 81 (2022), 35349–35377. https://doi.org/10.1007/s11042-021-11863-3 doi: 10.1007/s11042-021-11863-3
[16]	T. Ohta, K. Kawasaki, Equilibrium morphology of block copolymer melts, Macromolecules, 19 (1986), 2621–2632. https://doi.org/10.1021/ma00164a028 doi: 10.1021/ma00164a028
[17]	Y. Li, Q. Xia, C. Lee, S. Kim, J. Kim, A robust and efficient fingerprint image restoration method based on a phase-field model, Pattern Recognit., 123 (2022), 108405. https://doi.org/10.1016/j.patcog.2021.108405 doi: 10.1016/j.patcog.2021.108405
[18]	J. Zhang, C. Chen, X. F. Yang, Efficient and energy stable method for the Cahn-Hilliard phase-field model for diblock copolymers, Appl. Numer. Math., 151 (2020), 263–281. https://doi.org/10.1016/j.apnum.2019.12.006 doi: 10.1016/j.apnum.2019.12.006
[19]	Y. Nishiura, I. Ohnishi, Some mathematical aspects of the micro-phase separation in diblock copolymers, Phys. D, 85 (1995), 31–39. https://doi.org/10.1016/0167-2789(95)00005-O doi: 10.1016/0167-2789(95)00005-O
[20]	A. Miranville, The Cahn-Hilliard equation and some of its variants, AIMS Math., 2 (2022), 479–544. https://doi.org/10.3934/Math.2017.2.479 doi: 10.3934/Math.2017.2.479
[21]	R. Scala, G. F. Schimperna, On the viscous Cahn-Hilliard equation with singular potential and inertial term, AIMS Math., 1 (2016), 64–76. https://doi.org/10.3934/Math.2016.1.64 doi: 10.3934/Math.2016.1.64
[22]	J. Yang, C. Lee, D. Jeong, J. Kim, A simple and explicit numerical method for the phase-field model for diblock copolymer melts, Comput. Mater. Sci., 205 (2022), 111192. https://doi.org/10.1016/j.commatsci.2022.111192 doi: 10.1016/j.commatsci.2022.111192
[23]	Q. Du, L. Ju, X. Li, Z. Qiao, Stabilized linear semi-implicit schemes for the nonlocal Cahn-Hilliard equation, J. Comput. Phys., 363 (2018), 39–54. https://doi.org/10.1016/j.jcp.2018.02.023 doi: 10.1016/j.jcp.2018.02.023
[24]	Y. Li, S. Lan, X. Liu, B. Lu, L. Wang, An efficient volume repairing method by using a modified Allen-Cahn equation, Pattern Recognit., 107 (2020), 107478. https://doi.org/10.1016/j.patcog.2020.107478 doi: 10.1016/j.patcog.2020.107478

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)