G-MSGINet: A Grouped Multi-Scale Graph-Involution Network for Contactless Fingerprint Recognition

2025-05-13

AI Summary

To address the reliance on multi-branch architectures, directional label supervision, and complex preprocessing in contactless fingerprint identification—particularly for minutiae localization and identity embedding—this paper proposes an end-to-end single-stream framework. Its core innovation is the Graph-based Multi-Scale Grouped Involution (GMSGI) layer, which jointly integrates pixel-wise grouped involution, dynamic multi-scale kernel generation, and graph relational modeling. This enables adaptive fingerprint region graph construction, direction-supervision-free precise minutiae localization, and co-optimized identity embedding. Evaluated on three major benchmarks—including PolyU—the framework achieves a minutiae detection F1-score of 0.83±0.02, Rank-1 accuracy of 97.0%–99.1%, and an extremely low equal-error rate (EER) of 0.5%. With only 0.38M parameters, it improves upon state-of-the-art F1-scores by up to 4.8%.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents G-MSGINet, a unified and efficient framework for robust contactless fingerprint recognition that jointly performs minutiae localization and identity embedding directly from raw input images. Existing approaches rely on multi-branch architectures, orientation labels, or complex preprocessing steps, which limit scalability and generalization across real-world acquisition scenarios. In contrast, the proposed architecture introduces the GMSGI layer, a novel computational module that integrates grouped pixel-level involution, dynamic multi-scale kernel generation, and graph-based relational modelling into a single processing unit. Stacked GMSGI layers progressively refine both local minutiae-sensitive features and global topological representations through end-to-end optimization. The architecture eliminates explicit orientation supervision and adapts graph connectivity directly from learned kernel descriptors, thereby capturing meaningful structural relationships among fingerprint regions without fixed heuristics. Extensive experiments on three benchmark datasets, namely PolyU, CFPose, and Benchmark 2D/3D, demonstrate that G-MSGINet consistently achieves minutiae F1-scores in the range of $0.83pm0.02$ and Rank-1 identification accuracies between 97.0% and 99.1%, while maintaining an Equal Error Rate (EER) as low as 0.5%. These results correspond to improvements of up to 4.8% in F1-score and 1.4% in Rank-1 accuracy when compared to prior methods, using only 0.38 million parameters and 6.63 giga floating-point operations, which represents up to ten times fewer parameters than competitive baselines. This highlights the scalability and effectiveness of G-MSGINet in real-world contactless biometric recognition scenarios.

Problem

• Robust contactless fingerprint recognition without complex preprocessing
• Joint minutiae localization and identity embedding from raw images
• Overcoming scalability and generalization limits in existing approaches

Innovation

• Grouped pixel-level involution for feature extraction
• Dynamic multi-scale kernel generation
• Graph-based relational modelling without fixed heuristics