Towards Fingerprint Mosaicking Artifact Detection: A Self-Supervised Deep Learning Approach

2025-01-09

AI Summary

To address performance degradation in fingerprint matching caused by stitching artifacts, this paper proposes an unsupervised self-supervised deep learning framework that detects and quantifies quality-degraded regions in contact-based, rolling, and contactless fingerprint images—without requiring manual annotations. The method integrates contrastive learning-driven fingerprint feature encoding, multimodal representation alignment, and a joint artifact localization–severity regression network. It further introduces the first fingerprint stitching artifact scoring mechanism. Evaluated across heterogeneous devices and modalities, the approach demonstrates superior robustness and achieves high-accuracy artifact detection and precise spatial localization across diverse fingerprint acquisition modalities. By enabling fully automated image quality assessment, it significantly enhances the accuracy and reliability of biometric recognition 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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

Fingerprint mosaicking, which is the process of combining multiple fingerprint images into a single master fingerprint, is an essential process in modern biometric systems. However, it is prone to errors that can significantly degrade fingerprint image quality. This paper proposes a novel deep learning-based approach to detect and score mosaicking artifacts in fingerprint images. Our method leverages a self-supervised learning framework to train a model on large-scale unlabeled fingerprint data, eliminating the need for manual artifact annotation. The proposed model effectively identifies mosaicking errors, achieving high accuracy on various fingerprint modalities, including contactless, rolled, and pressed fingerprints and furthermore proves to be robust to different data sources. Additionally, we introduce a novel mosaicking artifact score to quantify the severity of errors, enabling automated evaluation of fingerprint images. By addressing the challenges of mosaicking artifact detection, our work contributes to improving the accuracy and reliability of fingerprint-based biometric systems.

Problem

• Fingerprint recognition
• Artifact detection
• Image splicing

Innovation

• Deep Learning
• Fingerprint Splicing Artifact Detection
• Automated Quality Assessment