FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis

TL;DR

This paper introduces FPBench, a comprehensive benchmark for evaluating multimodal large language models on fingerprint analysis tasks, highlighting the impact of fine-tuning on model performance.

Contribution

It presents FPBench, the first benchmark for fingerprint analysis with MLLMs, and demonstrates how fine-tuning enhances model effectiveness in biometric tasks.

Findings

Fine-tuning improves performance by 7%-39%.

Evaluated 20 MLLMs across 7 datasets and 8 tasks.

Benchmark serves as a first step towards foundation models in fingerprints.

Abstract

Multimodal LLMs (MLLMs) are capable of performing complex data analysis, visual question answering, generation, and reasoning tasks. However, their ability to analyze biometric data is relatively underexplored. In this work, we investigate the effectiveness of MLLMs in understanding fine structural and textural details present in fingerprint images. To this end, we design a comprehensive benchmark, FPBench, to evaluate 20 MLLMs (open-source and proprietary models) across 7 real and synthetic datasets on a suite of 8 biometric and forensic tasks (e.g., pattern analysis, fingerprint verification, real versus synthetic classification, etc.) using zero-shot and chain-of-thought prompting strategies. We further fine-tune vision and language encoders on a subset of open-source MLLMs to demonstrate domain adaptation. FPBench is a novel benchmark designed as a first step towards developing foundation models in fingerprints. Our findings indicate fine-tuning of vision and language encoders improves the performance by 7%-39%. Our codes are available at https://github.com/Ektagavas/FPBench.