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

2025-06-02

AI Summary

To address degraded matching performance in contactless fingerprint recognition caused by defocus, low ridge-valley contrast, and pose/perspective distortions, this paper proposes Ridgeformer: a hierarchical Transformer architecture trained via multi-stage contrastive learning. Ridgeformer introduces a novel hierarchical feature alignment mechanism—first modeling global spatial structure, then refining local ridge alignment through end-to-end differentiable ridge-line attention. It further incorporates cross-domain feature disentanglement and multi-stage contrastive loss to enable fine-grained matching across contact and contactless domains. Evaluated on HKPolyU and RidgeBase, Ridgeformer achieves up to 12.7% improvement in Rank-1 accuracy under both contactless-to-contact and contactless-to-contactless protocols, significantly outperforming state-of-the-art methods and commercial off-the-shelf (COTS) systems.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Tracking, profiling, and countermeasures against them
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Enhancing contactless fingerprint recognition accuracy
• Addressing out-of-focus and low-contrast fingerprint images
• Improving cross-domain fingerprint matching reliability

Innovation

• Multi-stage transformer-based fingerprint matching
• Hierarchical feature extraction and alignment
• Global and localized feature refinement