Fixed-Length Dense Fingerprint Representation

TL;DR

This work tackles robust fingerprint matching under diverse modalities and quality levels by proposing FLARE, a fixed-length dense descriptor framework augmented with pose-based alignment and dual enhancement. The fixed-length dense representation (FDRN) preserves spatial fidelity and foreground-background separation, while dual pose estimators and dual enhancement modules (UNetEnh and PriorEnh) improve alignment and ridge clarity without altering the fingerprint modality. FLARE achieves state-of-the-art or competitive results across rolled, plain, latent, and contactless fingerprints, with strong ablations demonstrating the value of each component and their complementary effects. The approach offers a scalable solution for large-scale fingerprint matching, enabling efficient, reliable cross-modality recognition with practical applicability in real-world security systems.

Abstract

Fixed-length fingerprint representations, which map each fingerprint to a compact and fixed-size feature vector, are computationally efficient and well-suited for large-scale matching. However, designing a robust representation that effectively handles diverse fingerprint modalities, pose variations, and noise interference remains a significant challenge. In this work, we propose a fixed-length dense descriptor of fingerprints, and introduce FLARE-a fingerprint matching framework that integrates the Fixed-Length dense descriptor with pose-based Alignment and Robust Enhancement. This fixed-length representation employs a three-dimensional dense descriptor to effectively capture spatial relationships among fingerprint ridge structures, enabling robust and locally discriminative representations. To ensure consistency within this dense feature space, FLARE incorporates pose-based alignment using complementary estimation methods, along with dual enhancement strategies that refine ridge clarity while preserving the original fingerprint modality. The proposed dense descriptor supports fixed-length representation while maintaining spatial correspondence, enabling fast and accurate similarity computation. Extensive experiments demonstrate that FLARE achieves superior performance across rolled, plain, latent, and contactless fingerprints, significantly outperforming existing methods in cross-modality and low-quality scenarios. Further analysis validates the effectiveness of the dense descriptor design, as well as the impact of alignment and enhancement modules on the accuracy of dense descriptor matching. Experimental results highlight the effectiveness and generalizability of FLARE as a unified and scalable solution for robust fingerprint representation and matching. The implementation and code will be publicly available at https://github.com/Yu-Yy/FLARE.

Figures (18)

• Figure 1: Comparison of one-dimensional and dense descriptors. One-dimensional descriptors lose spatial structural information, whereas dense descriptors maintain spatial correspondence, enhancing local sensitivity and discriminative power while mitigating background noise.
• Figure 2: Visual comparison of enhancement methods. Each row shows an original fingerprint (left), the result from a representative existing method (middle), and our enhancement (right). Compared to previous methods, which may hallucinate background ridges (top) nist2020verifinger, over-generate ridges in blurry regions (middle) FingerGAN, or exhibit block artifacts (bottom) tang2017fingernet, our approach preserves the original impression style, suppresses background interference, and avoids introducing spurious textures.
• Figure 3: FLARE matching pipeline. Each image is processed through two pose estimators and two enhancers, yielding four descriptor pairs. The final score is the maximum of four cosine similarities.
• Figure 4: Examples of fingerprint degradation simulation.
• Figure 5: The architecture illustration of PriorEnh.