Joint Identity Verification and Pose Alignment for Partial Fingerprints

TL;DR

This paper introduces a joint framework using a multi-task CNN-Transformer network to simultaneously verify partial fingerprints and estimate their relative pose, significantly improving accuracy and efficiency over existing methods.

Contribution

It proposes a novel joint approach for fingerprint verification and pose alignment, leveraging their correlation with a multi-task CNN-Transformer model and a specialized pre-training task.

Findings

Achieves state-of-the-art accuracy in partial fingerprint verification.

Provides precise relative pose estimation for partial fingerprints.

Demonstrates improved efficiency compared to previous methods.

Abstract

Currently, portable electronic devices are becoming more and more popular. For lightweight considerations, their fingerprint recognition modules usually use limited-size sensors. However, partial fingerprints have few matchable features, especially when there are differences in finger pressing posture or image quality, which makes partial fingerprint verification challenging. Most existing methods regard fingerprint position rectification and identity verification as independent tasks, ignoring the coupling relationship between them -- relative pose estimation typically relies on paired features as anchors, and authentication accuracy tends to improve with more precise pose alignment. In this paper, we propose a novel framework for joint identity verification and pose alignment of partial fingerprint pairs, aiming to leverage their inherent correlation to improve each other. To achieve this, we present a multi-task CNN (Convolutional Neural Network)-Transformer hybrid network, and design a pre-training task to enhance the feature extraction capability. Experiments on multiple public datasets (NIST SD14, FVC2002 DB1A & DB3A, FVC2004 DB1A & DB2A, FVC2006 DB1A) and an in-house dataset show that our method achieves state-of-the-art performance in both partial fingerprint verification and relative pose estimation, while being more efficient than previous methods.