Latent Fingerprint Matching via Dense Minutia Descriptor

TL;DR

This paper introduces a deep-learning based dense minutia descriptor for latent fingerprint matching, improving accuracy on challenging low-quality fingerprints by capturing detailed local and texture information.

Contribution

The study proposes a novel deep-learning dense minutia descriptor that enhances latent fingerprint matching accuracy and interpretability over previous methods.

Findings

Achieves state-of-the-art performance on multiple datasets.

Provides a more representative and interpretable descriptor.

Incorporates segmentation to focus on foreground regions.

Abstract

Latent fingerprint matching is a daunting task, primarily due to the poor quality of latent fingerprints. In this study, we propose a deep-learning based dense minutia descriptor (DMD) for latent fingerprint matching. A DMD is obtained by extracting the fingerprint patch aligned by its central minutia, capturing detailed minutia information and texture information. Our dense descriptor takes the form of a three-dimensional representation, with two dimensions associated with the original image plane and the other dimension representing the abstract features. Additionally, the extraction process outputs the fingerprint segmentation map, ensuring that the descriptor is only valid in the foreground region. The matching between two descriptors occurs in their overlapping regions, with a score normalization strategy to reduce the impact brought by the differences outside the valid area. Our descriptor achieves state-of-the-art performance on several latent fingerprint datasets. Overall, our DMD is more representative and interpretable compared to previous methods.