UoU: A Universal Fingerprint Foundation Model Based on Large-Scale Unsupervised Learning

2026-06-15

AI Summary

This work proposes the first foundational model framework for fingerprint recognition, addressing the limitations of traditional methods that rely on task-specific, isolated pipelines and struggle to generalize across sensors, image qualities, and downstream tasks. The framework establishes a multi-level representation system encompassing image restoration, structural fields, semantic landmarks, point-wise features, and global descriptors. It integrates orientation flow and ridge frequency modeling with spatial equivariance constraints, and employs a joint training strategy combining supervised warm-up, weakly supervised expansion, and unsupervised consolidation. This architecture enables multi-task learning and architecture-agnostic scalability, unifying diverse tasks—including matching, alignment, enhancement, and registration—within a single framework, thereby significantly improving cross-scenario generalization and representation stability.

Abstract

Fingerprint recognition is still dominated by task-specific pipelines, where enhancement, structural parsing, alignment, and matching are optimized in isolation. Although effective in narrow settings, this design limits representation reuse across sensors, qualities, and downstream applications. We therefore present UoU, short for ``a \textbf{U}niversal fingerprint foundation model based \textbf{o}n large-scale \textbf{U}nsupervised learning,'' which reframes fingerprint feature extraction as a domain-specific foundation-model problem. UoU is organized around a multi-level representation hierarchy spanning image restoration, structural fields, semantic tokens, point-level biometric entities, and compact global descriptors. Its training recipe combines a supervised cold start on precise annotations, large-scale weakly supervised refinement, and large-scale unsupervised consolidation, with the latter two stages iterated during large-scale training so that weak supervision broadens semantic coverage while unsupervised learning stabilizes correspondences, invariances, and representation geometry. Rather than treating fingerprint imagery as generic texture, UoU exploits domain-specific symmetries and intermediate structure, including orientation flow, periodic ridge patterns, sparse biometric entities, and spatial equivariance. The framework is intentionally architecture-agnostic: while the present study includes an initial transformer-based structured-prediction instantiation, the broader design supports multi-task learning, scalable model configurations, and downstream specialization for matching, alignment, enhancement, registration, and related fingerprint applications. This paper presents the technical motivation, system design, and validation protocol of UoU, and part of the baseline implementation is publicly available at https://github.com/XiongjunGuan/UoU.

Problem

• fingerprint recognition
• foundation model
• representation reuse
• unsupervised learning
• domain-specific

Innovation

• foundation model
• unsupervised learning
• fingerprint recognition
• multi-level representation
• domain-specific prior