Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security

Biometric systems such as fingerprint recognition encounter significant challenges under wet conditions or small fingerprints, where noise degrades recognition accuracy. These challenges increase false acceptance rates (FARs) and false rejection rates (FRRs) as conventional denoising models designed...

Full description

Saved in:
Bibliographic Details
Main Authors: Mao-Hsiu Hsu, Ying-Hong Shi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/92/1/64
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471900219080704
author Mao-Hsiu Hsu
Ying-Hong Shi
author_facet Mao-Hsiu Hsu
Ying-Hong Shi
author_sort Mao-Hsiu Hsu
collection DOAJ
description Biometric systems such as fingerprint recognition encounter significant challenges under wet conditions or small fingerprints, where noise degrades recognition accuracy. These challenges increase false acceptance rates (FARs) and false rejection rates (FRRs) as conventional denoising models designed for larger fingerprints cannot handle the smaller and noisier samples in portable and embedded devices. In this study, we collected 71,188 wet–dry fingerprints using a capacitive sensor. Fingerprints in sizes of 176 × 36, 88 × 88, and 80 × 100 pixels were preprocessed by padding and cropping them to a uniform size of 48 × 48 pixels. Preprocessing was conducted to standardize and augment the data and enhance the model’s ability to generalize across diverse data types. We developed a wet fingerprint denoising network (WFDN), a multi-stage neural network designed to improve wet fingerprint quality for small and large samples. By integrating scale-invariant feature transform, WFDN effectively restores critical minutiae and significantly enhances feature preservation compared with existing models. The network also incorporates an automatic label classifier and cyclic multi-variate functions to reduce noise. Despite its compact architecture, WFDN demonstrates superior performance, reducing the FRR from 19.6 to 8.4% for small fingerprints. Moreover, assessment results using NIST fingerprint image quality 2.0 (NFIQ2) for larger fingerprints show notable improvements in system reliability. The proposed model improves biometric processing significantly. WFDN represents a significant advancement in fingerprint-based identification, offering improved performance and robustness in challenging conditions.
format Article
id doaj-art-53d33c9f2ec1411fa99fc8689175624b
institution Kabale University
issn 2673-4591
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-53d33c9f2ec1411fa99fc8689175624b2025-08-20T03:24:40ZengMDPI AGEngineering Proceedings2673-45912025-05-019216410.3390/engproc2025092064Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric SecurityMao-Hsiu Hsu0Ying-Hong Shi1Department of Electro-Optical Engineering, National Formosa University, Yunlin 632, TaiwanDepartment of Electro-Optical Engineering, National Formosa University, Yunlin 632, TaiwanBiometric systems such as fingerprint recognition encounter significant challenges under wet conditions or small fingerprints, where noise degrades recognition accuracy. These challenges increase false acceptance rates (FARs) and false rejection rates (FRRs) as conventional denoising models designed for larger fingerprints cannot handle the smaller and noisier samples in portable and embedded devices. In this study, we collected 71,188 wet–dry fingerprints using a capacitive sensor. Fingerprints in sizes of 176 × 36, 88 × 88, and 80 × 100 pixels were preprocessed by padding and cropping them to a uniform size of 48 × 48 pixels. Preprocessing was conducted to standardize and augment the data and enhance the model’s ability to generalize across diverse data types. We developed a wet fingerprint denoising network (WFDN), a multi-stage neural network designed to improve wet fingerprint quality for small and large samples. By integrating scale-invariant feature transform, WFDN effectively restores critical minutiae and significantly enhances feature preservation compared with existing models. The network also incorporates an automatic label classifier and cyclic multi-variate functions to reduce noise. Despite its compact architecture, WFDN demonstrates superior performance, reducing the FRR from 19.6 to 8.4% for small fingerprints. Moreover, assessment results using NIST fingerprint image quality 2.0 (NFIQ2) for larger fingerprints show notable improvements in system reliability. The proposed model improves biometric processing significantly. WFDN represents a significant advancement in fingerprint-based identification, offering improved performance and robustness in challenging conditions.https://www.mdpi.com/2673-4591/92/1/64biometric securitywet fingerprintsdenoisingneural networksfingerprint recognition
spellingShingle Mao-Hsiu Hsu
Ying-Hong Shi
Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
Engineering Proceedings
biometric security
wet fingerprints
denoising
neural networks
fingerprint recognition
title Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
title_full Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
title_fullStr Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
title_full_unstemmed Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
title_short Optimizing Wet Fingerprint Denoising Net for Enhanced Biometric Security
title_sort optimizing wet fingerprint denoising net for enhanced biometric security
topic biometric security
wet fingerprints
denoising
neural networks
fingerprint recognition
url https://www.mdpi.com/2673-4591/92/1/64
work_keys_str_mv AT maohsiuhsu optimizingwetfingerprintdenoisingnetforenhancedbiometricsecurity
AT yinghongshi optimizingwetfingerprintdenoisingnetforenhancedbiometricsecurity