Learning a Fixed-Length Fingerprint Representation

TL;DR

DeepPrint is a deep learning model that creates a compact, fixed-length fingerprint representation, enabling fast and accurate identification even with poor quality fingerprints, outperforming traditional methods in speed and security.

Contribution

The paper introduces DeepPrint, a novel deep network that learns a fixed-length, highly discriminative fingerprint representation incorporating domain knowledge, improving speed and security over existing variable-length methods.

Findings

DeepPrint achieves comparable accuracy to top commercial matchers.

It significantly reduces matching time to 0.3 seconds for large datasets.

DeepPrint's representation is the most compact and discriminative reported in literature.

Abstract

We present DeepPrint, a deep network, which learns to extract fixed-length fingerprint representations of only 200 bytes. DeepPrint incorporates fingerprint domain knowledge, including alignment and minutiae detection, into the deep network architecture to maximize the discriminative power of its representation. The compact, DeepPrint representation has several advantages over the prevailing variable length minutiae representation which (i) requires computationally expensive graph matching techniques, (ii) is difficult to secure using strong encryption schemes (e.g. homomorphic encryption), and (iii) has low discriminative power in poor quality fingerprints where minutiae extraction is unreliable. We benchmark DeepPrint against two top performing COTS SDKs (Verifinger and Innovatrics) from the NIST and FVC evaluations. Coupled with a re-ranking scheme, the DeepPrint rank-1 search accuracy on the NIST SD4 dataset against a gallery of 1.1 million fingerprints is comparable to the top COTS matcher, but it is significantly faster (DeepPrint: 98.80% in 0.3 seconds vs. COTS A: 98.85% in 27 seconds). To the best of our knowledge, the DeepPrint representation is the most compact and discriminative fixed-length fingerprint representation reported in the academic literature.