Deep Learning for Vein Biometric Recognition on a Smartphone

García-Martín, Raúl; Sanchez-Reillo, Raul

Publication:
Deep Learning for Vein Biometric Recognition on a Smartphone

dc.affiliation.dpto	UC3M. Departamento de Tecnología Electrónica	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Universitario de Tecnologías de Identificación (GUTI)	es
dc.contributor.author	García-Martín, Raúl
dc.contributor.author	Sanchez-Reillo, Raul
dc.date.accessioned	2021-12-20T09:53:09Z
dc.date.available	2021-12-20T09:53:09Z
dc.date.issued	2021-07-08
dc.description.abstract	The ongoing COVID-19 pandemic has pointed out, even more, the important need for hygiene contactless biometric recognition systems. Vein-based devices are great non-contact options although they have not been entirely well-integrated in daily life. In this work, in an attempt to contribute to the research and development of these devices, a contactless wrist vein recognition system with a real-life application is revealed. A Transfer Learning (TL) method, based on different Deep Convolutional Neural Networks architectures, for Vascular Biometric Recognition (VBR), has been designed and tested, for the first time in a research approach, on a smartphone. TL is a Deep Learning (DL) technique that could be divided into networks as feature extractor, i.e., using a pre-trained (different large-scale dataset) Convolutional Neural Network (CNN) to obtain unique features that then, are classified with a traditional Machine Learning algorithm, and fine-tuning, i.e., training a CNN that has been initialized with weights of a pre-trained (different large-scale dataset) CNN. In this study, a feature extractor base method has been employed. Several architecture networks have been tested on different wrist vein datasets: UC3M-CV1, UC3M-CV2, and PUT. The DL model has been integrated on the Xiaomi© Pocophone F1 and the Xiaomi© Mi 8 smartphones obtaining high biometric performance, up to 98% of accuracy and less than 0.4% of EER with a 50–50% train-test on UC3M-CV2, and fast identification/verification time, less than 300 milliseconds. The results infer, high DL performance and integration reachable in VBR without direct user-device contact, for real-life applications nowadays.	en
dc.format.extent	21
dc.identifier.bibliographicCitation	Garcia-Martin, R. & Sanchez-Reillo, R. (2021). Deep Learning for Vein Biometric Recognition on a Smartphone. IEEE Access, 9, 98812–98832.	en
dc.identifier.doi	https://doi.org/10.1109/ACCESS.2021.3095666
dc.identifier.issn	2169-3536
dc.identifier.publicationfirstpage	98812
dc.identifier.publicationlastpage	98832
dc.identifier.publicationtitle	IEEE Access	en
dc.identifier.publicationvolume	9
dc.identifier.uri	https://hdl.handle.net/10016/33798
dc.identifier.uxxi	AR/0000028863
dc.language.iso	eng
dc.publisher	IEEE	en
dc.rights	© The Author(s) 2021. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.	en
dc.rights	Atribución 3.0 España	*
dc.rights.accessRights	open access	es
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/es/	*
dc.subject.eciencia	Electrónica	es
dc.subject.other	Vein biometric recognition	en
dc.subject.other	Smartphone	en
dc.subject.other	Deep learning	en
dc.subject.other	Convolutional neural network (CNN)	en
dc.subject.other	Machine learning	en
dc.subject.other	Transfer learning	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Contactless wrist vascular database	en
dc.subject.other	Neural network as feature extractor	en
dc.subject.other	Biometrics on mobile devices	en
dc.title	Deep Learning for Vein Biometric Recognition on a Smartphone	en
dc.type	research article	*
dc.type.hasVersion	VoR	*
dspace.entity.type	Publication