TU Darmstadt / ULB / TUbiblio

Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability

Priesnitz, Jannis ; Casula, Roberto ; Kolberg, Jascha ; Fang, Meiling ; Madhu, Akhila ; Rathgeb, Christian ; Marcialis, Gian Luca ; Damer, Naser ; Busch, Christoph (2024)
Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability.
In: IEEE Transactions on Biometrics, Behavior, and Identity Science
doi: 10.1109/TBIOM.2024.3403770
Article, Bibliographie

Abstract

Contactless fingerprint recognition is an emerging biometric technology that has several advantages over contact-based schemes, such as improved user acceptance and fewer hygienic concerns. Like for most other biometrics, Presentation Attack Detection (PAD) is crucial to preserving the trustworthiness of contactless fingerprint recognition methods. For many contactless biometric characteristics, Convolutional Neural Networks (CNNs) represent the state-of-the-art of PAD algorithms. For CNNs, the ability to accurately classify samples that are not included in the training is of particular interest, since these generalization capabilities indicate robustness in real-world scenarios. In this work, we focus on the generalizability and explainability aspects of CNN-based contactless fingerprint PAD methods. Based on previously obtained findings, we selected four CNN-based methods for contactless fingerprint PAD: two PAD methods designed for other biometric characteristics, an algorithm for contact-based fingerprint PAD and a general-purpose ResNet18. For our evaluation, we use four databases and partition them using Leave-One-Out (LOO) protocols. Furthermore, the generalization capability to a newly captured database is tested. Moreover, we explore t-SNE plots as a means of explainability to interpret our results in more detail. The low D-EERs obtained from the LOO experiments (below 0.1% D-EER for every LOO group) indicate that the selected algorithms are well-suited for the particular application. However, with an D-EER of 4.14%, the generalization experiment still has room for improvement.

Item Type: Article
Erschienen: 2024
Creators: Priesnitz, Jannis ; Casula, Roberto ; Kolberg, Jascha ; Fang, Meiling ; Madhu, Akhila ; Rathgeb, Christian ; Marcialis, Gian Luca ; Damer, Naser ; Busch, Christoph
Type of entry: Bibliographie
Title: Mobile Contactless Fingerprint Presentation Attack Detection: Generalizability and Explainability
Language: English
Date: 2024
Journal or Publication Title: IEEE Transactions on Biometrics, Behavior, and Identity Science
DOI: 10.1109/TBIOM.2024.3403770
URL / URN: https://doi.org/10.1109/TBIOM.2024.3403770
Abstract:

Contactless fingerprint recognition is an emerging biometric technology that has several advantages over contact-based schemes, such as improved user acceptance and fewer hygienic concerns. Like for most other biometrics, Presentation Attack Detection (PAD) is crucial to preserving the trustworthiness of contactless fingerprint recognition methods. For many contactless biometric characteristics, Convolutional Neural Networks (CNNs) represent the state-of-the-art of PAD algorithms. For CNNs, the ability to accurately classify samples that are not included in the training is of particular interest, since these generalization capabilities indicate robustness in real-world scenarios. In this work, we focus on the generalizability and explainability aspects of CNN-based contactless fingerprint PAD methods. Based on previously obtained findings, we selected four CNN-based methods for contactless fingerprint PAD: two PAD methods designed for other biometric characteristics, an algorithm for contact-based fingerprint PAD and a general-purpose ResNet18. For our evaluation, we use four databases and partition them using Leave-One-Out (LOO) protocols. Furthermore, the generalization capability to a newly captured database is tested. Moreover, we explore t-SNE plots as a means of explainability to interpret our results in more detail. The low D-EERs obtained from the LOO experiments (below 0.1% D-EER for every LOO group) indicate that the selected algorithms are well-suited for the particular application. However, with an D-EER of 4.14%, the generalization experiment still has room for improvement.

Uncontrolled Keywords: Biometrics, Machine learning, Fingerprint recognition, Spoofing attacks
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Date Deposited: 11 Jun 2024 10:08
Last Modified: 11 Jun 2024 10:34
PPN: 51902902X
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details