Please use this identifier to cite or link to this item: http://www.repositorio.ufop.br/handle/123456789/10397
Title: Learning deep off-the-person heart biometrics representations.
Authors: Luz, Eduardo José da Silva
Moreira, Gladston Juliano Prates
Oliveira, Luiz Eduardo Soares de
Schwartz, William Robson
Gomes, David Menotti
Keywords: Electrocardiogram
Off-the-person category
Biometric systems
Deep learning
Issue Date: 2018
Citation: LUZ, E. J. da S. et al. Learning deep off-the-person heart biometrics representations. IEEE Transactions on Information Forensics and Security, v. 13, n. 5, p. 1258-1270, mai. 2018. Disponível em: <https://ieeexplore.ieee.org/document/8219706/>. Acesso em: 16 jun. 2018.
Abstract: Since the beginning of the new millennium, the electrocardiogram (ECG) has been studied as a biometric trait for security systems and other applications. Recently, with devices such as smartphones and tablets, the acquisition of ECG signal in the off-the-person category has made this biometric signal suitable for real scenarios. In this paper, we introduce the usage of deep learning techniques, specifically convolutional networks, for extracting useful representation for heart biometrics recognition. Particularly, we investigate the learning of feature representations for heart biometrics through two sources: on the raw heartbeat signal and on the heartbeat spectrogram. We also introduce heartbeat data augmentation techniques, which are very important to generalization in the context of deep learning approaches. Using the same experimental setup for six methods in the literature, we show that our proposal achieves state-of-the-art results in the two off-the-person publicly available databases.
URI: http://www.repositorio.ufop.br/handle/123456789/10397
metadata.dc.identifier.uri2: https://ieeexplore.ieee.org/document/8219706/authors
ISSN: 15566013
Appears in Collections:DECOM - Artigos publicados em periódicos

Files in This Item:
File Description SizeFormat 
ARTIGO_LearningDeepPerson.pdf3,46 MBAdobe PDFView/Open    Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.