pith. sign in

arxiv: 2605.15796 · v1 · pith:RLVLE42Unew · submitted 2026-05-15 · 💻 cs.CV

Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion

Xiongjun Guan , Jianjiang Feng , Jie Zhou This is my paper

Pith reviewed 2026-05-20 18:35 UTC · model grok-4.3

classification 💻 cs.CV
keywords fingerprint registration3D-2D cross-modalpoint cloud fusionpose normalizationunwrappingbiometric matchingridge structurecontactless fingerprint
0
0 comments X

The pith

A unified framework preprocesses and registers 3D fingerprints with both contactless and contact-based 2D fingerprints using nonparametric unwrapping and point-cloud fusion.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper presents a framework to bridge 3D and 2D fingerprint modalities by preprocessing 3D data for compatibility with existing 2D systems. The approach avoids contact deformation issues in 3D captures while preserving ridge details. It combines nonparametric unwrapping of point clouds to 2D, fusion of multiple 3D views, pose normalization, and targeted registration. If successful, it would let high-accuracy 3D fingerprints work with legacy databases and matchers. Experiments on 150 fingers confirm low fusion errors and improved matching.

Core claim

The framework achieves ridge-level 3D registration accuracy and robust pose estimation through a nonparametric visualization and unwrapping method, a point-cloud fusion pipeline, ellipse-based pose normalization, and a pose-aware cross-modal registration strategy. On a database of 150 fingers, 3D fusion error is around 0.09 mm, contactless registration reaches ridge-scale accuracy, and pose-aware unwrapping boosts genuine matching scores compared to generic methods. This supports 3D fingerprints as a geometric bridge between modalities.

What carries the argument

The nonparametric visualization and unwrapping method that converts 3D fingerprint point clouds into rolled-equivalent 2D representations without a global finger-shape model, together with the point-cloud fusion and pose-aware registration pipeline.

Load-bearing premise

The nonparametric visualization and unwrapping method can convert a 3D fingerprint point cloud into a rolled-equivalent 2D representation without relying on a global finger-shape model.

What would settle it

Measuring the 3D fusion error on the 150-finger database and finding it significantly larger than 0.09 mm, or finding no gain in genuine matching scores from pose-aware unwrapping, would falsify the performance claims.

Figures

Figures reproduced from arXiv: 2605.15796 by Jianjiang Feng, Jie Zhou, Xiongjun Guan.

Figure 1
Figure 1. Figure 1: Overall workflow of the proposed framework. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Examples of 3D fingerprint visualization results. [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visualization before and after nonparametric unwrap [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visualization of seam penalties used in point-cloud [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Example of pose estimation for contact-based 2D–3D [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: Fingerprint acquisition devices used in the experiments. [PITH_FULL_IMAGE:figures/full_fig_p007_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: Histogram of point-cloud registration errors for 3D [PITH_FULL_IMAGE:figures/full_fig_p008_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Representative failure cases for 3D point-cloud reg [PITH_FULL_IMAGE:figures/full_fig_p008_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Ellipse fitting and center-axis estimation on representative thumb and index-finger point clouds. [PITH_FULL_IMAGE:figures/full_fig_p009_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Representative thumb pose-normalization errors for [PITH_FULL_IMAGE:figures/full_fig_p009_13.png] view at source ↗
Figure 16
Figure 16. Figure 16: Comparison of genuine matching scores between [PITH_FULL_IMAGE:figures/full_fig_p010_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Representative deformation-field comparisons between direct unwrapping and pose-aware unwrapping. [PITH_FULL_IMAGE:figures/full_fig_p011_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Representative improvement of contactless-to-contact [PITH_FULL_IMAGE:figures/full_fig_p012_18.png] view at source ↗
read the original abstract

Three-dimensional (3D) fingerprints preserve global finger geometry and local ridge structure while avoiding contact-induced deformation, but they remain difficult to integrate with legacy two-dimensional (2D) fingerprint systems. This paper addresses the intermediate stage between 3D acquisition and cross-modal matching, and presents a unified framework for 3D fingerprint preprocessing and registration across contactless and contact-based 2D modalities. The framework combines four components: 1) a nonparametric visualization and unwrapping method that converts a 3D fingerprint point cloud into a rolled-equivalent 2D representation without relying on a global finger-shape model; 2) a point-cloud fusion pipeline that registers and mosaics multiple partial 3D captures into a more complete fingerprint model; 3) an ellipse-based pose normalization method for canonical finger alignment; and 4) a pose-aware cross-modal registration strategy that improves compatibility between 3D fingerprints and both contactless and contact-based 2D fingerprints. Experiments on a self-collected multimodal fingerprint database containing 150 fingers show that the proposed framework achieves ridge-level 3D registration accuracy, robust pose estimation, and consistent gains in 2D compatibility. In particular, the 3D fusion error is concentrated around 0.09 mm, contactless 2D--3D registration reaches ridge-scale projection accuracy, and pose-aware unwrapping improves genuine matching scores relative to generic 3D unwrapping. These results support the use of 3D fingerprints as an effective geometric bridge across heterogeneous fingerprint modalities.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents a unified framework for preprocessing and cross-modal registration of 3D fingerprints with both contactless and contact-based 2D fingerprints. The framework consists of four components: (1) a nonparametric visualization and unwrapping method that converts a 3D point cloud into a rolled-equivalent 2D representation without a global finger-shape model; (2) a point-cloud fusion pipeline for registering and mosaicking multiple partial 3D captures; (3) an ellipse-based pose normalization method; and (4) a pose-aware cross-modal registration strategy. Experiments on a self-collected database of 150 fingers report a 3D fusion error of approximately 0.09 mm, ridge-scale projection accuracy for contactless 2D–3D registration, and improved genuine matching scores from pose-aware unwrapping compared to generic 3D unwrapping.

Significance. If the nonparametric unwrapping and fusion components deliver the claimed ridge-level accuracy without implicit shape priors, the work would provide a practical bridge between emerging 3D fingerprint acquisition and legacy 2D systems, potentially improving compatibility and matching performance while avoiding contact-induced deformation. The self-collected multimodal dataset and quantitative fusion error metric are concrete strengths that could support follow-on research in cross-modal biometrics.

major comments (2)
  1. [Abstract and §3] Abstract and §3 (method description): The central claim that component 1 performs nonparametric unwrapping 'without relying on a global finger-shape model' is load-bearing for all downstream accuracy claims (0.09 mm fusion error, ridge-scale projection, and matching gains), yet the manuscript provides no algorithmic specification of how local curvature, partial captures, or out-of-distribution finger geometries are handled without implicit priors. This omission prevents verification that the reported improvements are not artifacts of limited geometric variation in the 150-finger set.
  2. [Experiments] Experiments section: The reported gains in genuine matching scores and 0.09 mm fusion error are presented without baseline comparisons to prior 3D unwrapping or registration methods, without error bars, and without statistical significance tests. This makes it impossible to determine whether the pose-aware components produce improvements beyond what generic 3D-to-2D projection already achieves.
minor comments (2)
  1. [Abstract] The abstract states results on '150 fingers' but does not specify exclusion criteria, capture conditions, or demographic coverage; adding these details would strengthen reproducibility.
  2. [§3.3] Notation for the ellipse-based pose normalization (component 3) should be defined explicitly with respect to the point-cloud coordinate system before the registration equations.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments and for recognizing the potential of our unified framework to bridge 3D and 2D fingerprint modalities. We address each major comment below and describe the revisions we will incorporate.

read point-by-point responses

  1. Referee: [Abstract and §3] Abstract and §3 (method description): The central claim that component 1 performs nonparametric unwrapping 'without relying on a global finger-shape model' is load-bearing for all downstream accuracy claims (0.09 mm fusion error, ridge-scale projection, and matching gains), yet the manuscript provides no algorithmic specification of how local curvature, partial captures, or out-of-distribution finger geometries are handled without implicit priors. This omission prevents verification that the reported improvements are not artifacts of limited geometric variation in the 150-finger set.

    Authors: We agree that greater algorithmic detail in §3 would strengthen verifiability of the nonparametric claim. The unwrapping procedure operates exclusively on local surface normals and geodesic distances computed directly from the input point cloud, without fitting any global parametric shape. For partial captures, overlapping local patches are aligned via ICP before unwrapping proceeds. To address the referee’s concern, we will expand §3 with explicit pseudocode, additional equations for local curvature handling, and a short discussion of behavior on out-of-distribution geometries. These additions will make clear that no implicit global priors are introduced beyond the local geometry present in each capture. revision: yes

  2. Referee: [Experiments] Experiments section: The reported gains in genuine matching scores and 0.09 mm fusion error are presented without baseline comparisons to prior 3D unwrapping or registration methods, without error bars, and without statistical significance tests. This makes it impossible to determine whether the pose-aware components produce improvements beyond what generic 3D-to-2D projection already achieves.

    Authors: We acknowledge that the current experimental presentation would benefit from explicit baselines and statistical support. In the revised manuscript we will add quantitative comparisons against representative prior 3D unwrapping techniques, report standard deviations as error bars on all fusion and projection metrics, and include paired statistical tests (e.g., Wilcoxon signed-rank) on the genuine matching-score improvements. These changes will allow readers to assess whether the pose-aware components yield gains beyond generic projection. revision: yes

Circularity Check

0 steps flagged

No circularity: experimental framework with independent validation on collected data

full rationale

The paper describes an applied computer-vision framework with four algorithmic components for 3D-to-2D fingerprint registration. All performance claims (0.09 mm fusion error, ridge-scale projection accuracy, improved genuine matching scores) are presented as direct experimental outcomes measured on a self-collected 150-finger multimodal database. No equations, predictions, or first-principles derivations are given that reduce by construction to fitted parameters or to the target result itself. The nonparametric unwrapping claim is an algorithmic assertion whose correctness is tested empirically rather than presupposed; no self-citation chain, uniqueness theorem, or ansatz smuggling is invoked to justify core steps. The derivation chain is therefore self-contained and externally falsifiable via the reported metrics.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based on the abstract alone, the framework relies on standard computer-vision assumptions about point-cloud alignment and surface unwrapping; no explicit free parameters, new axioms, or invented entities are stated.

pith-pipeline@v0.9.0 · 5822 in / 1495 out tokens · 74102 ms · 2026-05-20T18:35:32.768848+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

61 extracted references · 61 canonical work pages

  1. [1]

    Maltoni, D

    D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar,Handbook of Fingerprint Recognition. Springer, 2009

    work page 2009

  2. [2]

    3d touchless fin- gerprints: Compatibility with legacy rolled images,

    Y . Chen, G. Parziale, E. Diaz-Santana, and A. K. Jain, “3d touchless fin- gerprints: Compatibility with legacy rolled images,” in2006 Biometrics Symposium, 2006, pp. 1–6

    work page 2006

  3. [3]

    3d to 2d fingerprints: Unrolling and distortion correction,

    Q. Zhao, A. Jain, and G. Abramovich, “3d to 2d fingerprints: Unrolling and distortion correction,” in2011 International Joint Conference on Biometrics, 2011, pp. 1–8

    work page 2011

  4. [4]

    Fit-sphere unwrapping and performance analysis of 3d fingerprints,

    Y . Wang, D. L. Lau, and L. G. Hassebrook, “Fit-sphere unwrapping and performance analysis of 3d fingerprints,”Applied Optics, vol. 49, no. 4, pp. 592–600, 2010

    work page 2010

  5. [5]

    Fast 3-d fingertip reconstruction using a single two-view structured light acquisition,

    R. D. Labati, A. Genovese, V . Piuri, and F. Scotti, “Fast 3-d fingertip reconstruction using a single two-view structured light acquisition,” in2011 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications, 2011, pp. 1–8

    work page 2011

  6. [6]

    Quality measurement of unwrapped three-dimensional finger- prints: A neural networks approach,

    ——, “Quality measurement of unwrapped three-dimensional finger- prints: A neural networks approach,” in2012 International Joint Con- ference on Neural Networks, 2012, pp. 1–8

    work page 2012

  7. [7]

    Performance improvisation on 3d converted 2d unraveled fingerprint,

    R. Anitha and N. Sesireka, “Performance improvisation on 3d converted 2d unraveled fingerprint,”IOSR Journal of Computer Engineering, vol. 16, no. 6, pp. 50–56, 2014

    work page 2014

  8. [8]

    R. R. Dighade,Approach to Unwrap a 3D Fingerprint to a 2D Equivalent. University of Maryland, Baltimore County, 2012

    work page 2012

  9. [9]

    Acquiring a 2d rolled equivalent fingerprint image from a non-contact 3d finger scan,

    A. Fatehpuria, D. L. Lau, and L. G. Hassebrook, “Acquiring a 2d rolled equivalent fingerprint image from a non-contact 3d finger scan,” in Biometric Technology for Human Identification III, vol. 6202, 2006, p. 62020C

    work page 2006

  10. [10]

    A new approach to unwrap a 3-d fingerprint to a 2-d rolled equivalent fingerprint,

    S. Shafaei, T. Inanc, and L. G. Hassebrook, “A new approach to unwrap a 3-d fingerprint to a 2-d rolled equivalent fingerprint,” in2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems, 2009, pp. 1–5

    work page 2009

  11. [11]

    Monocular 3d fingerprint reconstruction and unwarping,

    Z. Cui, J. Feng, and J. Zhou, “Monocular 3d fingerprint reconstruction and unwarping,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 7, pp. 8679–8695, 2023

    work page 2023

  12. [12]

    Pose-specific 3d fingerprint unfolding,

    X. Guan, J. Feng, and J. Zhou, “Pose-specific 3d fingerprint unfolding,” inChinese Conference on Biometric Recognition. Springer, 2021, pp. 185–194

    work page 2021

  13. [13]

    Distortion-tolerant filter for elastic-distorted fingerprint matching,

    C. I. Watson, P. J. Grother, and D. P. Casasent, “Distortion-tolerant filter for elastic-distorted fingerprint matching,” inOptical Pattern Recogni- tion XI, vol. 4043, 2000, pp. 166–174

    work page 2000

  14. [14]

    Detection and rectification of distorted fingerprints,

    X. Si, J. Feng, J. Zhou, and Y . Luo, “Detection and rectification of distorted fingerprints,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 3, pp. 555–568, 2015

    work page 2015

  15. [15]

    Fingerprint distortion rectification using deep convolutional neural networks,

    A. Dabouei, H. Kazemi, S. M. Iranmanesh, J. M. Dawson, and N. M. Nasrabadi, “Fingerprint distortion rectification using deep convolutional neural networks,” in2018 International Conference on Biometrics, 2018, pp. 1–8

    work page 2018

  16. [16]

    Deep contactless fingerprint unwarping,

    A. Dabouei, S. Soleymani, J. Dawson, and N. M. Nasrabadi, “Deep contactless fingerprint unwarping,” in2019 International Conference on Biometrics, 2019, pp. 1–8

    work page 2019

  17. [17]

    A minutia-based partial fingerprint recognition system,

    T.-Y . Jea and V . Govindaraju, “A minutia-based partial fingerprint recognition system,”Pattern Recognition, vol. 38, no. 10, pp. 1672– 1684, 2005

    work page 2005

  18. [18]

    A new algorithm for distorted finger- prints matching based on normalized fuzzy similarity measure,

    X. Chen, J. Tian, and X. Yang, “A new algorithm for distorted finger- prints matching based on normalized fuzzy similarity measure,”IEEE Transactions on Image Processing, vol. 15, no. 3, pp. 767–776, 2006

    work page 2006

  19. [19]

    A robust matching method for distorted fingerprints,

    X. Zheng, Y . Wang, and X. Zhao, “A robust matching method for distorted fingerprints,” in2007 IEEE International Conference on Image Processing, vol. 2, 2007, pp. II–377–II–380

    work page 2007

  20. [20]

    Local relative location error descriptor-based fingerprint minutiae matching,

    X. Tong, S. Liu, J. Huang, and X. Tang, “Local relative location error descriptor-based fingerprint minutiae matching,”Pattern Recognition Letters, vol. 29, no. 3, pp. 286–294, 2008

    work page 2008

  21. [21]

    Fingerprint matching by thin-plate spline modelling of elastic deformations,

    A. M. Bazen and S. H. Gerez, “Fingerprint matching by thin-plate spline modelling of elastic deformations,”Pattern Recognition, vol. 36, no. 8, pp. 1859–1867, 2003

    work page 2003

  22. [22]

    Image versus feature mosaicing: A case study in fingerprints,

    A. Ross, S. Shah, and J. Shah, “Image versus feature mosaicing: A case study in fingerprints,” inBiometric Technology for Human Identification III, vol. 6202, 2006, p. 620208

    work page 2006

  23. [23]

    Dense registration of fingerprints,

    X. Si, J. Feng, B. Yuan, and J. Zhou, “Dense registration of fingerprints,” Pattern Recognition, vol. 63, pp. 87–101, 2017

    work page 2017

  24. [24]

    2-d phase demodulation for deformable fingerprint registration,

    Z. Cui, J. Feng, S. Li, J. Lu, and J. Zhou, “2-d phase demodulation for deformable fingerprint registration,”IEEE Transactions on Information Forensics and Security, vol. 13, no. 12, pp. 3153–3165, 2018

    work page 2018

  25. [25]

    Dense fingerprint registration via displacement regression network,

    Z. Cui, J. Feng, and J. Zhou, “Dense fingerprint registration via displacement regression network,” in2019 International Conference on Biometrics, 2019, pp. 1–8

    work page 2019

  26. [26]

    Dense registration and mosaicking of fingerprints by training an end-to-end network,

    ——, “Dense registration and mosaicking of fingerprints by training an end-to-end network,”IEEE Transactions on Information Forensics and Security, vol. 16, pp. 627–642, 2020

    work page 2020

  27. [27]

    A fingerprint verification system based on triangu- lar matching and dynamic time warping,

    Z. M. Kovacs-Vajna, “A fingerprint verification system based on triangu- lar matching and dynamic time warping,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1266–1276, 2000

    work page 2000

  28. [28]

    Minutia cylinder-code: A new representation and matching technique for fingerprint recognition,

    R. Cappelli, M. Ferrara, and D. Maltoni, “Minutia cylinder-code: A new representation and matching technique for fingerprint recognition,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 12, pp. 2128–2141, 2010

    work page 2010

  29. [29]

    An algorithm for distorted fingerprint matching based on local triangle feature set,

    X. Chen, J. Tian, X. Yang, and Y . Zhang, “An algorithm for distorted fingerprint matching based on local triangle feature set,”IEEE Transac- tions on Information Forensics and Security, vol. 1, no. 2, pp. 169–177, 2006

    work page 2006

  30. [30]

    Combining minutiae descriptors for fingerprint matching,

    J. Feng, “Combining minutiae descriptors for fingerprint matching,” Pattern Recognition, vol. 41, no. 1, pp. 342–352, 2008

    work page 2008

  31. [31]

    Minutiae-based match- ing state model for combinations in fingerprint matching system,

    X. Cheng, S. Tulyakov, and V . Govindaraju, “Minutiae-based match- ing state model for combinations in fingerprint matching system,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013, pp. 92–97

    work page 2013

  32. [32]

    Direct regression of distortion field from a single fingerprint image,

    X. Guan, Y . Duan, J. Feng, and J. Zhou, “Direct regression of distortion field from a single fingerprint image,” in2022 International Joint Conference on Biometrics, 2022, pp. 1–8

    work page 2022

  33. [33]

    Regression of dense distortion field from a single fingerprint image,

    ——, “Regression of dense distortion field from a single fingerprint image,”IEEE Transactions on Information Forensics and Security, vol. 18, pp. 4377–4390, 2023

    work page 2023

  34. [34]

    Latent fingerprint registration via matching densely sampled points,

    S. Gu, J. Feng, J. Lu, and J. Zhou, “Latent fingerprint registration via matching densely sampled points,”IEEE Transactions on Information Forensics and Security, vol. 16, pp. 1231–1244, 2021

    work page 2021

  35. [35]

    Phase-aggregated dual-branch network for efficient fingerprint dense registration,

    X. Guan, J. Feng, and J. Zhou, “Phase-aggregated dual-branch network for efficient fingerprint dense registration,”IEEE Transactions on Infor- mation Forensics and Security, vol. 19, pp. 5712–5724, 2024

    work page 2024

  36. [36]

    Estimating 3d finger angle via fingerprint image,

    K. He, Y . Duan, J. Feng, and J. Zhou, “Estimating 3d finger angle via fingerprint image,”Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 6, no. 1, pp. 14:1–14:22, 2022

    work page 2022

  37. [37]

    Estimating 3d finger pose via 2d-3d fingerprint matching,

    Y . Duan, K. He, J. Feng, J. Lu, and J. Zhou, “Estimating 3d finger pose via 2d-3d fingerprint matching,” inProceedings of the 27th International Conference on Intelligent User Interfaces, 2022, pp. 459–469

    work page 2022

  38. [38]

    Estimating fingerprint pose via dense voting,

    Y . Duan, J. Feng, J. Lu, and J. Zhou, “Estimating fingerprint pose via dense voting,”IEEE Transactions on Information Forensics and Security, vol. 18, pp. 2493–2507, 2023

    work page 2023

  39. [39]

    Finger pose estimation for under- screen fingerprint sensor,

    X. Guan, Z. Pan, J. Feng, and J. Zhou, “Finger pose estimation for under- screen fingerprint sensor,”IEEE Transactions on Information Forensics and Security, vol. 20, pp. 12 739–12 753, 2025

    work page 2025

  40. [40]

    Mclfiq: Mobile contactless fingerprint image qual- ity,

    J. Priesnitz, A. Weißenfeld, L. Ruzicka, C. Rathgeb, B. Strobl, R. Less- mann, and C. Busch, “Mclfiq: Mobile contactless fingerprint image qual- ity,”IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 6, no. 2, pp. 272–287, 2024

    work page 2024

  41. [41]

    Contactless fingerprint recognition guided by 3d finger pose,

    H. Pei, Z. Pan, X. Guan, J. Feng, and J. Zhou, “Contactless fingerprint recognition guided by 3d finger pose,” in2025 IEEE International Joint Conference on Biometrics, 2025, pp. 1–9

    work page 2025

  42. [42]

    The surround imager tm: A multi-camera touchless device to acquire 3d rolled-equivalent fingerprints,

    G. Parziale, E. Diaz-Santana, and R. Hauke, “The surround imager tm: A multi-camera touchless device to acquire 3d rolled-equivalent fingerprints,” inInternational Conference on Biometrics. Springer, 2006, pp. 244–250

    work page 2006

  43. [43]

    Data acquisition and processing of 3-d fingerprints,

    Y . Wang, L. G. Hassebrook, and D. L. Lau, “Data acquisition and processing of 3-d fingerprints,”IEEE Transactions on Information Forensics and Security, vol. 5, no. 4, pp. 750–760, 2010

    work page 2010

  44. [44]

    3d fingerprint image acquisition methods,

    A. Kumar, “3d fingerprint image acquisition methods,” inContactless 3D Fingerprint Identification. Springer, 2018, pp. 17–27

    work page 2018

  45. [45]

    Full 3d touchless fingerprint recognition: Sensor, database and baseline performance,

    J. Galbally, G. Bostrom, and L. Beslay, “Full 3d touchless fingerprint recognition: Sensor, database and baseline performance,” in2017 IEEE International Joint Conference on Biometrics, 2017, pp. 225–233

    work page 2017

  46. [46]

    3d fingerprint phan- toms,

    S. S. Arora, K. Cao, A. K. Jain, and N. G. Paulter, “3d fingerprint phan- toms,” in2014 22nd International Conference on Pattern Recognition, 2014, pp. 684–689

    work page 2014

  47. [47]

    A novel system and experimental study for 3d finger multibiometrics,

    W. Yang, Z. Chen, J. Huang, and W. Kang, “A novel system and experimental study for 3d finger multibiometrics,”IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 4, no. 4, pp. 471– 485, 2022

    work page 2022

  48. [48]

    3d fingerprint reconstruction system using feature correspondences and prior estimated finger model,

    F. Liu and D. Zhang, “3d fingerprint reconstruction system using feature correspondences and prior estimated finger model,”Pattern Recognition, vol. 47, no. 1, pp. 178–193, 2014. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY , DRAFT MANUSCRIPT 14

    work page 2014

  49. [49]

    Toward unconstrained fingerprint recognition: A fully touchless 3-d system based on two views on the move,

    R. D. Labati, A. Genovese, V . Piuri, and F. Scotti, “Toward unconstrained fingerprint recognition: A fully touchless 3-d system based on two views on the move,”IEEE transactions on systems, Man, and cybernetics: systems, vol. 46, no. 2, pp. 202–219, 2015

    work page 2015

  50. [50]

    Towards contactless, low-cost and accurate 3d fingerprint identification,

    A. Kumar and C. Kwong, “Towards contactless, low-cost and accurate 3d fingerprint identification,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 3438–3443

    work page 2013

  51. [51]

    Bridging dimensions in fingerprints to advance distinctiveness: Recovering 3d minutiae from a single contactless 2d fingerprint image,

    C. Dong and A. Kumar, “Bridging dimensions in fingerprints to advance distinctiveness: Recovering 3d minutiae from a single contactless 2d fingerprint image,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 9, pp. 7812–7831, 2025

    work page 2025

  52. [52]

    Latent fingerprint matching via dense minutia descriptor,

    Z. Pan, Y . Duan, X. Guan, J. Feng, and J. Zhou, “Latent fingerprint matching via dense minutia descriptor,” in2024 IEEE International Joint Conference on Biometrics, 2024, pp. 1–10

    work page 2024

  53. [53]

    Fixed-length dense descriptor for efficient fingerprint matching,

    Z. Pan, Y . Duan, J. Feng, and J. Zhou, “Fixed-length dense descriptor for efficient fingerprint matching,” in2024 IEEE International Workshop on Information Forensics and Security, 2024, pp. 1–6

    work page 2024

  54. [54]

    Fixed-length dense fingerprint representation with alignment and robust enhancement,

    Z. Pan, X. Guan, Y . Duan, J. Feng, and J. Zhou, “Fixed-length dense fingerprint representation with alignment and robust enhancement,” IEEE Transactions on Information Forensics and Security, 2026

    work page 2026

  55. [55]

    (2021) Verifinger

    Neurotechnology Inc. (2021) Verifinger. [Online]. Available: http: //www.neurotechnology.com

    work page 2021

  56. [56]

    A spectral technique for correspondence problems using pairwise constraints,

    M. Leordeanu and M. Hebert, “A spectral technique for correspondence problems using pairwise constraints,” inTenth IEEE International Con- ference on Computer Vision (ICCV’05) Volume 1, vol. 2. IEEE, 2005, pp. 1482–1489

    work page 2005

  57. [57]

    Object modelling by registration of multiple range images,

    Y . Chen and G. Medioni, “Object modelling by registration of multiple range images,”Image and Vision Computing, vol. 10, no. 3, pp. 145– 155, 1992

    work page 1992

  58. [58]

    Method for registration of 3-d shapes,

    P. J. Besl and N. D. McKay, “Method for registration of 3-d shapes,” in Sensor Fusion IV: Control Paradigms and Data Structures, vol. 1611, 1992, pp. 586–606

    work page 1992

  59. [59]

    (2021) pcregrigid documentation

    MathWorks. (2021) pcregrigid documentation. [Online]. Available: https://ww2.mathworks.cn/help/vision/ref/pcregrigid.html

    work page 2021

  60. [60]

    Decomposition of transformation matrices for robot vision,

    S. Ganapathy, “Decomposition of transformation matrices for robot vision,”Pattern Recognition Letters, vol. 2, no. 6, pp. 401–412, 1984

    work page 1984

  61. [61]

    Faugeras,Three-Dimensional Computer Vision: A Geometric View- point

    O. Faugeras,Three-Dimensional Computer Vision: A Geometric View- point. MIT Press, 1993

    work page 1993