Identity-Consistent Multi-Pose Generation of Contactless Fingerprints

2026-05-05

AI Summary

This work addresses the challenges of nonlinear geometric distortions caused by unconstrained finger poses and cross-modal domain discrepancies between contactless and contact-based fingerprints. To this end, the authors propose IMPOSE, a novel framework that uniquely integrates physical modeling with generative AI to synthesize identity-consistent, multi-pose contactless fingerprints through a three-stage pipeline: roll-wise generation via a latent diffusion model, cross-modal translation using Sauvola’s locally adaptive binarization, and physically grounded pose simulation based on a 3D finger model. The method preserves minutiae topology and spatial alignment while substantially improving cross-modal matching performance, achieving state-of-the-art results with EERs of 8.74% and 2.26% on the UWA and PolyU CL2CB datasets, respectively, and delivering consistent gains across mainstream models such as DeepPrint and AFRNet.

Abstract

Contactless fingerprint recognition has gained increasing attention due to its advantages in hygiene and acquisition flexibility. However, the absence of physical contact constraints introduces severe nonlinear geometric distortions caused by free finger poses in 3D space, resulting in a substantial cross-modal domain gap between contactless and conventional contact-based fingerprints. Existing solutions largely rely on explicit geometric correction or image enhancement, which are fragile under extreme pose variations. In this paper, we propose Identity-Consistent Multi-Pose Generation of Contactless Fingerprints (IMPOSE), a physics-inspired framework that synthesizes identity-preserving, multi-pose contactless fingerprint samples to empower recognition models. IMPOSE consists of three stages: (1) rolled fingerprint identity generation via latent diffusion with discrete codebook representations, (2) cross-modal translation from rolled to contactless modality guided by Sauvola-based local adaptive binarization as an identity anchor, and (3) physics-based multi-pose simulation through 3D finger model texture mapping and projection. The generated samples maintain strict identity consistency at the ridge topology level and spatial alignment with standard fingerprint coordinate space. Extensive experiments on the UWA and PolyU CL2CB databases demonstrate that fine-tuning fixed-length dense descriptors (FDD) with IMPOSE-synthesized data achieves state-of-the-art cross-modal matching, reducing EER to 8.74% on UWA and 2.26% on PolyU CL2CB. Synthetic data also yields consistent gains across mainstream representations including DeepPrint and AFRNet, and the hybrid strategy combining synthetic and real data achieves the best overall results. The code and generated samples are available at https://github.com/Yu-Yy/IMPOSE.

Problem

• contactless fingerprint
• geometric distortion
• cross-modal domain gap
• fingerprint recognition
• pose variation

Innovation

• contactless fingerprint
• identity-consistent generation
• latent diffusion
• cross-modal translation
• physics-based simulation