AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching

In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed Sabah Ahmed AL-Jumaili, Huda Kadhim Tayyeh, Abeer Alsadoon
Format: Article
Language:English
Published: University of Baghdad, College of Science for Women 2023-12-01
Series:مجلة بغداد للعلوم
Subjects:
Online Access:https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/8362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705373576986624
author Ahmed Sabah Ahmed AL-Jumaili
Huda Kadhim Tayyeh
Abeer Alsadoon
author_facet Ahmed Sabah Ahmed AL-Jumaili
Huda Kadhim Tayyeh
Abeer Alsadoon
author_sort Ahmed Sabah Ahmed AL-Jumaili
collection DOAJ
description In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compared to traditional image filtering techniques. This paper aimed to utilize a specific CNN architecture known as AlexNet for the fingerprint-matching task. Using such an architecture, this study has extracted the significant features of the fingerprint image, generated a key based on such a biometric feature of the image, and stored it in a reference database. Then, using Cosine similarity and Hamming Distance measures, the testing fingerprints have been matched with a reference. Using the FVC2002 database, the proposed method showed a False Acceptance Rate (FAR) of 2.09% and a False Rejection Rate (FRR) of 2.81%. Comparing these results against other studies that utilized traditional approaches such as the Fuzzy Vault has demonstrated the efficacy of CNN in terms of fingerprint matching. It is also emphasizing the usefulness of using Cosine similarity and Hamming Distance in terms of matching.
format Article
id doaj-art-0d2cbe2b13ba434bb2bdd991aadfb042
institution DOAJ
issn 2078-8665
2411-7986
language English
publishDate 2023-12-01
publisher University of Baghdad, College of Science for Women
record_format Article
series مجلة بغداد للعلوم
spelling doaj-art-0d2cbe2b13ba434bb2bdd991aadfb0422025-08-20T03:16:29ZengUniversity of Baghdad, College of Science for Womenمجلة بغداد للعلوم2078-86652411-79862023-12-01206(Suppl.)10.21123/bsj.2023.8362AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric MatchingAhmed Sabah Ahmed AL-Jumaili0Huda Kadhim Tayyeh1Abeer Alsadoon2Department of Business Information Technology, College of Business Informatics, University of Information Technology and Communications, Baghdad, Iraq.Department of Informatics Systems Management, College of Business Informatics, University of Information Technology and Communications, Baghdad, Iraq.School of Computing, Mathematics and Engineering, Charles Sturt University, Australia (CSU) & School of Computer Data and Mathematical Sciences, Western Sydney University (WSU), Sydney, Australia & Asia Pacific International College (APIC), Sydney, Australia. In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compared to traditional image filtering techniques. This paper aimed to utilize a specific CNN architecture known as AlexNet for the fingerprint-matching task. Using such an architecture, this study has extracted the significant features of the fingerprint image, generated a key based on such a biometric feature of the image, and stored it in a reference database. Then, using Cosine similarity and Hamming Distance measures, the testing fingerprints have been matched with a reference. Using the FVC2002 database, the proposed method showed a False Acceptance Rate (FAR) of 2.09% and a False Rejection Rate (FRR) of 2.81%. Comparing these results against other studies that utilized traditional approaches such as the Fuzzy Vault has demonstrated the efficacy of CNN in terms of fingerprint matching. It is also emphasizing the usefulness of using Cosine similarity and Hamming Distance in terms of matching. https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/8362Biometric Cryptosystem, Convolutional Neural Network, Cosine Similarity, Fingerprint Matching, Information Security
spellingShingle Ahmed Sabah Ahmed AL-Jumaili
Huda Kadhim Tayyeh
Abeer Alsadoon
AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
مجلة بغداد للعلوم
Biometric Cryptosystem, Convolutional Neural Network, Cosine Similarity, Fingerprint Matching, Information Security
title AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
title_full AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
title_fullStr AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
title_full_unstemmed AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
title_short AlexNet Convolutional Neural Network Architecture with Cosine and Hamming Similarity/Distance Measures for Fingerprint Biometric Matching
title_sort alexnet convolutional neural network architecture with cosine and hamming similarity distance measures for fingerprint biometric matching
topic Biometric Cryptosystem, Convolutional Neural Network, Cosine Similarity, Fingerprint Matching, Information Security
url https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/8362
work_keys_str_mv AT ahmedsabahahmedaljumaili alexnetconvolutionalneuralnetworkarchitecturewithcosineandhammingsimilaritydistancemeasuresforfingerprintbiometricmatching
AT hudakadhimtayyeh alexnetconvolutionalneuralnetworkarchitecturewithcosineandhammingsimilaritydistancemeasuresforfingerprintbiometricmatching
AT abeeralsadoon alexnetconvolutionalneuralnetworkarchitecturewithcosineandhammingsimilaritydistancemeasuresforfingerprintbiometricmatching