CNN-Based Transfer Learning for 3D Knuckle Recognition

A trustworthy and secure identity verification system is in great demand nowadays. The automatic recognition of the 3D middle finger knuckle is a new biometric identifier that could offer a precise, practical, and efficient alternative for personal identification. According to earlier studies, deep...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammed Y. Shakor, Nigar M. Shafiq Surameery
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Advances in Multimedia
Online Access:http://dx.doi.org/10.1155/2023/6147422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849703697882284032
author Mohammed Y. Shakor
Nigar M. Shafiq Surameery
author_facet Mohammed Y. Shakor
Nigar M. Shafiq Surameery
author_sort Mohammed Y. Shakor
collection DOAJ
description A trustworthy and secure identity verification system is in great demand nowadays. The automatic recognition of the 3D middle finger knuckle is a new biometric identifier that could offer a precise, practical, and efficient alternative for personal identification. According to earlier studies, deep learning algorithms could be used for biometric identification. However, the accuracy of the current 3D middle finger knuckle recognition model is relatively low. Motivated by this fact, in this study, seven deep learning neural networks have been modified and trained to identify 3D middle finger knuckle patterns using transfer learning. Using the Hong Kong Polytechnic University’s 3D knuckle image dataset, an extensive experiment was performed. Two sessions of data from different camera lenses were used to assess the performance of the suggested deep learning model. The results show that the InceptionV3 method significantly enhanced the recognition of 3D middle finger knuckle patterns with 99.07% accuracy, followed by Xception, NasNetMobile, and DenseNet201 (97.35%, 92.92%, and 92.59%, respectively), which is superior to the current middle finger knuckle recognition model. This accurate, fast, and automatic middle finger knuckle identification will help to be implemented in real-time and small-scale settings like offices, schools, or personal devices like laptops and smartphones, where training is simple.
format Article
id doaj-art-1217d297fe574a4abeb14e18e9714eeb
institution DOAJ
issn 1687-5699
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Advances in Multimedia
spelling doaj-art-1217d297fe574a4abeb14e18e9714eeb2025-08-20T03:17:09ZengWileyAdvances in Multimedia1687-56992023-01-01202310.1155/2023/6147422CNN-Based Transfer Learning for 3D Knuckle RecognitionMohammed Y. Shakor0Nigar M. Shafiq Surameery1Department of EnglishInformation Technology DepartmentA trustworthy and secure identity verification system is in great demand nowadays. The automatic recognition of the 3D middle finger knuckle is a new biometric identifier that could offer a precise, practical, and efficient alternative for personal identification. According to earlier studies, deep learning algorithms could be used for biometric identification. However, the accuracy of the current 3D middle finger knuckle recognition model is relatively low. Motivated by this fact, in this study, seven deep learning neural networks have been modified and trained to identify 3D middle finger knuckle patterns using transfer learning. Using the Hong Kong Polytechnic University’s 3D knuckle image dataset, an extensive experiment was performed. Two sessions of data from different camera lenses were used to assess the performance of the suggested deep learning model. The results show that the InceptionV3 method significantly enhanced the recognition of 3D middle finger knuckle patterns with 99.07% accuracy, followed by Xception, NasNetMobile, and DenseNet201 (97.35%, 92.92%, and 92.59%, respectively), which is superior to the current middle finger knuckle recognition model. This accurate, fast, and automatic middle finger knuckle identification will help to be implemented in real-time and small-scale settings like offices, schools, or personal devices like laptops and smartphones, where training is simple.http://dx.doi.org/10.1155/2023/6147422
spellingShingle Mohammed Y. Shakor
Nigar M. Shafiq Surameery
CNN-Based Transfer Learning for 3D Knuckle Recognition
Advances in Multimedia
title CNN-Based Transfer Learning for 3D Knuckle Recognition
title_full CNN-Based Transfer Learning for 3D Knuckle Recognition
title_fullStr CNN-Based Transfer Learning for 3D Knuckle Recognition
title_full_unstemmed CNN-Based Transfer Learning for 3D Knuckle Recognition
title_short CNN-Based Transfer Learning for 3D Knuckle Recognition
title_sort cnn based transfer learning for 3d knuckle recognition
url http://dx.doi.org/10.1155/2023/6147422
work_keys_str_mv AT mohammedyshakor cnnbasedtransferlearningfor3dknucklerecognition
AT nigarmshafiqsurameery cnnbasedtransferlearningfor3dknucklerecognition