Capsule Network for Finger-Vein-based Biometric Identification

Basit Öğe Kaydı
dc.authorid0000-0001-7036-1723en_US
dc.contributor.authorGumusbas, Dilara
dc.contributor.authorYildirim, Tulay
dc.contributor.authorKocakulak, Mustafa
dc.contributor.authorAcır, Nurettin
dc.date.accessioned2021-03-20T20:12:45Z
dc.date.available2021-03-20T20:12:45Z
dc.date.issued2019
dc.departmentBTÜ, Mühendislik ve Doğa Bilimleri Fakültesi, Mekatronik Mühendisliği Bölümüen_US
dc.descriptionIEEE Symposium Series on Computational Intelligence (SSCI) -- DEC 06-09, 2019 -- Xiamen, PEOPLES R CHINAen_US
dc.description.abstractMost of the recent researches have determined that finger-vein identification systems have begun to change their direction from hand-crafted feature extraction to automatic feature extraction methods, such as convolutional neural networks (CNN). Although a few ongoing studies still concern handcrafted features, most of the recent works focus on automatic feature extraction via CNN-based algorithms, which has achieved breakthrough results. However, benchmark databases for finger-vein identification have a limited sample size per individual, which makes it difficult for them to capture the best representations in an individuals finger vein. Additionally, with the rise of spoofing attacks, obtaining the best representation of the finger vein has become even more important. Even though these algorithms adapt transfer learning by using pre-trained ImageNet weights, which create a general image feature space, it may be not the most optimal space for finger-vein identification. From this point of view, this paper firstly aims to use Capsule Network to take advantage of using convolutions with a limited number of samples on four finger-vein benchmark sub-databases. Moreover, it aims to extract finger-vein features that are more definable and rationally augments without using any pre-trained weights. Secondly, it compares the CNN-based equivalent and LeNet-5 models to show how Capsule Network is better at approaching representing features. This capsule-based finger-vein identification approach using 32x32 image resolutions achieves an average 95.5% accuracy on four benchmark sub-databases.en_US
dc.description.sponsorshipIEEE, IEEE Computat Intelligence Soc, Xiamen Univ, Xi AN Univ Posts & Telecommunicat, Fujian Assoc Artificial Intelligenceen_US
dc.identifier.endpage441en_US
dc.identifier.isbn978-1-7281-2485-8
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage437en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12885/686
dc.identifier.wosWOS:000555467200063en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.institutionauthorKocakulak, Mustafa
dc.institutionauthorAcır, Nurettin
dc.language.isoenen_US
dc.publisherIeeeen_US
dc.relation.ispartof2019 Ieee Symposium Series On Computational Intelligence (Ieee Ssci 2019)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectCapsule Networken_US
dc.subjectFinger-vein Identificationen_US
dc.subjectConvolutional Neural Networksen_US
dc.titleCapsule Network for Finger-Vein-based Biometric Identificationen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Elektrik Elektronik Mühendisliği Bölümü Yayın Koleksiyonu
Mekatronik Mühendisliği Bölümü Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu