Impact of Minutiae Errors in Latent Fingerprint Identification: Assessment and Prediction
Source abstract
Abstract
We study the impact of minutiae errors in the performance of latent fingerprint identification systems. We perform several experiments in which we remove ground-truth minutiae from latent fingerprints and evaluate the effects on matching score and rank-n identification using two different matchers and the popular NIST SD27 dataset. We observe how missing even one minutia from a fingerprint can have a significant negative impact on the identification performance. Our experimental results show that a fingerprint which has a top rank can be demoted to a bottom rank when two or more minutiae are missed. From our experimental results, we have noticed that some minutiae are more critical than others to correctly identify a latent fingerprint. Based on this finding, we have created a dataset to train several machine learning models trying to predict the impact of each minutia in the matching score of a fingerprint identification system. Finally, our best-trained model can successfully predict if a minutia will increase or decrease the matching score of a latent fingerprint.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Biometric Identification and Security · Face and Expression Recognition · Forensic and Genetic Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Altair Management Consultants Corp., 303 Wyman St., Suite 300, Waltham, MA 02451, USA
Tecnologico de Monterrey, Carretera al Lago de Guadalupe, Km. 3.5, Atizapán, Estado de Mexico 52926, Mexico
BiDA-Lab, Universidad Autonoma de Madrid, Ciudad Universitaria de Cantoblanco, 28049 Madrid, Spain
Funding
National Council of Science and Technology of Mexico
References (54)
Show source-provided references
1. Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View10.1109/ACCESS.2019.2949286 ↗
2. Fingerprint image enhancement and reconstruction using the orientation and phase reconstruction10.1016/j.ins.2020.01.031 ↗
3. Petrovska-Delacretaz, D., Chollet, G., and Dorizzi, B. (2009). Fingerprint Recognition. Guide to Biometric Reference Systems and Performance Evaluation, Springer.10.1007/978-1-84800-292-0 ↗
4. Jain, A.K., Flynn, P., and Ross, A.A. (2010). Handbook of Biometrics, Springer. [1st ed.].
5. Li, S.Z., and Jain, A.K. (2015). Fingerprint Databases and Evaluation. Encyclopedia of Biometrics, Springer.10.1007/978-1-4899-7488-4 ↗
6. Zabala-Blanco, D., Mora, M., Barrientos, R.J., Hernández-García, R., and Naranjo-Torres, J. (2020). Fingerprint Classification through Standard and Weighted Extreme Learning Machines. Appl. Sci., 10.10.3390/app10124125 ↗
7. Chen, J., Zhao, H., Cao, Z., Guo, F., and Pang, L. (2020). A Customized Semantic Segmentation Network for the Fingerprint Singular Point Detection. Appl. Sci., 10.10.3390/app10113868 ↗
8. Wang, Y., Gao, J., Li, Z., and Zhao, L. (2020). Robust and Accurate Wi-Fi Fingerprint Location Recognition Method Based on Deep Neural Network. Appl. Sci., 10.10.3390/app10010321 ↗
9. Pititheeraphab, Y., Thongpance, N., Aoyama, H., and Pintavirooj, C. (2020). Vein Pattern Verification and Identification Based on Local Geometric Invariants Constructed from Minutia Points and Augmented with Barcoded Local Feature. Appl. Sci., 10.10.3390/app10093192 ↗
10. Maltoni, D., Maio, D., Jain, A.K., and Prabhakar, S. (2009). Handbook of Fingerprint Recognition, Springer. [2nd ed.].10.1007/978-1-84882-254-2 ↗
11. Figueroa Mora, K.M., Anzurez Marín, J., Cerda, J., Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., and Olvera-López, J.A. (2020). Towards Inpainting and Denoising Latent Fingerprints: A Study on the Impact in Latent Fingerprint Identification. Pattern Recognition, Springer International Publishing.10.1007/978-3-030-49076-8 ↗
12. Bayesian analysis of fingerprint, face and signature evidences with automatic biometric systems10.1016/j.forsciint.2004.11.007 ↗
13. Improving Automated Latent Fingerprint Identification using Extended Minutia Types10.1016/j.inffus.2018.10.001 ↗
14. Efficient fingerprint matching on smart cards for high security and privacy in smart systems10.1016/j.ins.2017.12.038 ↗
15. Pre-registration of translated/distorted fingerprints based on correlation and the orientation field10.1016/j.ins.2020.02.017 ↗
16. Champod, C., Lennard, C., Margot, P., and Stoilovic, M. (2016). Fingerprints and Other Ridge Skin Impressions, CRC Press. [2nd ed.].10.1201/b20423 ↗
17. Tistarelli, M., and Champod, C. (2017). Handbook of Biometrics for Forensic Science, Springer.10.1007/978-3-319-50673-9 ↗
18. A comparative study of fingerprint image-quality estimation methods10.1109/TIFS.2007.908228 ↗
19. Latent fingerprint identification using deformable minutiae clustering10.1016/j.neucom.2015.05.130 ↗
20. Tistarelli, M., and Champod, C. (2017). From Biometric Scores to Forensic Likelihood Ratios. Handbook of Biometrics for Forensic Science, Springer.10.1007/978-3-319-50673-9 ↗
21. A Review of Fingerprint Feature Representations and Their Applications for Latent Fingerprint Identification: Trends and Evaluation10.1109/ACCESS.2019.2909497 ↗
22. A survey on minutiae-based palmprint feature representations, and a full analysis of palmprint feature representation role in latent identification performance10.1016/j.eswa.2019.04.018 ↗
23. Garris, M.D. (2000). NIST Special Database 27: Fingerprint Minutiae from Latent and Matching Tenprint Images, US Department of Commerce, National Institute of Standards and Technology.10.6028/NIST.IR.6534 ↗
24. Budowle, B., Buscaglia, J., and Perlman, R.S. (2006). Review of the scientific basis for friction ridge comparisons as a means of identification: Committee findings and recommendations. Forensic Sci. Commun., 8, Available online: https://go.gale.com/ps/anonymous?id=GALE|A144388747.
25. Signature Authentication based on Human Intervention: Performance and Complementarity with Automatic Systems10.1049/iet-bmt.2016.0115 ↗
26. Accuracy and reliability of forensic latent fingerprint decisions10.1073/pnas.1018707108 ↗
27. Changes in latent fingerprint examiners’ markup between analysis and comparison10.1016/j.forsciint.2014.11.021 ↗
28. Interexaminer variation of minutia markup on latent fingerprints10.1016/j.forsciint.2016.03.014 ↗
29. The impact of evidence lineups on fingerprint expert decisions10.1002/acp.3703 ↗
30. Valdes-Ramirez, D., Medina-Pérez, M.A., and Monroy, R. (2020). An ensemble of fingerprint matching algorithms based on cylinder codes and mtriplets for latent fingerprint identification. Pattern Anal. Appl., 1–12.10.1007/s10044-020-00911-7 ↗
31. Alonso-Fernandez, F., Fierrez-Aguilar, J., and Ortega-Garcia, J. (2005, January 15–17). An enhanced Gabor filter-based segmentation algorithm for fingerprint recognition systems. Proceedings of the IEEE International Symposium on Image and Signal Processing and Analysis, ISPA, Special Session on Signal and Image Processing for Biometrics, Zagreb, Croatia.10.1109/ISPA.2005.195416 ↗
32. Quality Measures in Biometric Systems
33. Combining multiple matchers for fingerprint verification: A case study in FVC2004
34. Multiple Classifiers in Biometrics. Part 1: Fundamentals and Review10.1016/j.inffus.2017.12.003 ↗
35. Image quality and position variability assessment in minutiae-based fingerprint verification10.1049/ip-vis:20031037 ↗
36. Ester, M., Kriegel, H.P., Sander, J., and Xu, X. (1996, January 2–6). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD-96), AAAI, Portland, OR, USA.
37. Grosz, S.A., Engelsma, J.J., Paulter, N.G., and Jain, A.K. (2019). White-box evaluation of fingerprint matchers: Robustness to minutiae perturbations. arXiv.10.1109/IJCB48548.2020.9304918 ↗
38. Cappelli, R., Maio, D., and Maltoni, D. (2004, January 22–23). SFinGe: An approach to synthetic fingerprint generation. Proceedings of the International Workshop on Biometric Technologies (BT2004), Calgary, AB, Canada.
39. Pre-Registration of Latent Fingerprints based on Orientation Field10.1049/iet-bmt.2014.0087 ↗
40. Watson, C.I., and Wilson, C.L. (1992). NIST Special Database 4, National Institute of Standards and Technology. Technical report.
41. Minutia Cylinder-Code: A New Representation and Matching Technique for Fingerprint Recognition10.1109/TPAMI.2010.52 ↗
42. Kittler, J., and Nixon, M.S. (2003). Face Recognition Vendor Test 2002 Performance Metrics. Audio- and Video-Based Biometric Person Authentication, Springer.10.1007/3-540-44887-X ↗
43. INTERPOL (2012). Guidelines concerning transmission of Fingerprint Crime Scene Marks, INTERPOL.
44. Quality-Based Conditional Processing in Multi-Biometrics: Application to Sensor Interoperability10.1109/TSMCA.2010.2047498 ↗
45. Fierrez-Aguilar, J., Chen, Y., Ortega-Garcia, J., and Jain, A.K. (2006, January 29). Incorporating image quality in multi-algorithm fingerprint verification. Proceedings of the IAPR International Conference on Biometrics, ICB, LNCS, New Delhi, India.10.1007/11608288_29 ↗
46. Fingerprint Image Quality Estimation and its Application to Multi-Algorithm Verification10.1109/TIFS.2008.920725 ↗
47. Multiple Classifiers in Biometrics. Part 2: Trends and Challenges10.1016/j.inffus.2017.12.005 ↗
48. Study on the impact of partition-induced dataset shift on k-fold cross-validation10.1109/TNNLS.2012.2199516 ↗
49. Introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
50. PBC4cip: A new contrast pattern-based classifier for class imbalance problems10.1016/j.knosys.2016.10.018 ↗
51. Random forests10.1023/A:1010933404324 ↗
52. Bagging predictors10.1007/BF00058655 ↗
53. Ridge Estimators in Logistic Regression10.2307/2347628 ↗
54. Support-vector networks10.1007/BF00994018 ↗