Ridgeformer: Mutli-Stage Contrastive Training For Fine-grained Cross-Domain Fingerprint Recognition

TL;DR

This paper introduces Ridgeformer, a multi-stage transformer-based approach for contactless fingerprint recognition that captures global and local features to improve accuracy across various challenging conditions.

Contribution

The paper presents a novel hierarchical transformer-based framework for fine-grained, cross-domain contactless fingerprint matching, addressing key challenges like image quality and perspective distortion.

Findings

Outperforms existing methods on HKPolyU and RidgeBase datasets.

Effective in contactless-to-contact and contactless-to-contactless matching scenarios.

Demonstrates robustness against image quality variations.

Abstract

The increasing demand for hygienic and portable biometric systems has underscored the critical need for advancements in contactless fingerprint recognition. Despite its potential, this technology faces notable challenges, including out-of-focus image acquisition, reduced contrast between fingerprint ridges and valleys, variations in finger positioning, and perspective distortion. These factors significantly hinder the accuracy and reliability of contactless fingerprint matching. To address these issues, we propose a novel multi-stage transformer-based contactless fingerprint matching approach that first captures global spatial features and subsequently refines localized feature alignment across fingerprint samples. By employing a hierarchical feature extraction and matching pipeline, our method ensures fine-grained, cross-sample alignment while maintaining the robustness of global feature representation. We perform extensive evaluations on publicly available datasets such as HKPolyU and RidgeBase under different evaluation protocols, such as contactless-to-contact matching and contactless-to-contactless matching and demonstrate that our proposed approach outperforms existing methods, including COTS solutions.