Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Types

TL;DR

This study benchmarks fixed-length fingerprint embeddings, analyzing how embedding size, sensor type, and image transformations affect biometric recognition performance, revealing an optimal embedding size and sensor differences.

Contribution

It investigates the optimal dimension for fingerprint embeddings and compares sensor types, providing insights into biometric performance and computational efficiency.

Findings

Optimal embedding size identified as 512 features.

Sensor type impacts recognition performance.

Embedding dimension reduction preserves high accuracy.

Abstract

Traditional minutiae-based fingerprint representations consist of a variable-length set of minutiae. This necessitates a more complex comparison causing the drawback of high computational cost in one-to-many comparison. Recently, deep neural networks have been proposed to extract fixed-length embeddings from fingerprints. In this paper, we explore to what extent fingerprint texture information contained in such embeddings can be reduced in terms of dimension while preserving high biometric performance. This is of particular interest since it would allow to reduce the number of operations incurred at comparisons. We also study the impact in terms of recognition performance of the fingerprint textural information for two sensor types, i.e. optical and capacitive. Furthermore, the impact of rotation and translation of fingerprint images on the extraction of fingerprint embeddings is analysed. Experimental results conducted on a publicly available database reveal an optimal embedding size of 512 feature elements for the texture-based embedding part of fixed-length fingerprint representations. In addition, differences in performance between sensor types can be perceived.