Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1111/exsy.12891 http://hdl.handle.net/11449/233847 |
Resumo: | Biometric recognition provides straightforward methods to deal with the problem of identifying people under certain circumstances. Additionally, a well-calibrated biometric system enhances security policies and prevents malicious attempts, such as fraud or identity theft. Deep learning has arisen to foster the problem by extracting high-level features that compose the so-called ‘user fingerprint’, that is, digital identification of a particular individual. Nevertheless, personal identification is not a trivial task, as many traits might define an individual, varying according to the task's domain. An exciting way to overcome such a problem is to employ handwritten dynamics, which are hand- and motor-based signals from an individual's writing style and obtained through a biometric smartpen. In this work, we propose using such signals to identify an individual through convolutional neural networks. Essentially, the proposed work uses a neighbour-based bag-of-samplings procedure to sample the signals to a fixed size and feeds them into a neural network responsible for extracting their features and further classifying them. The experiments were conducted over two handwritten dynamic datasets, NewHandPD and SignRec, and established new fruitful state-of-the-art concerning these particular datasets and the corresponding context. |
id |
UNSP_416ec2771c2395febd0bc6fcc264506c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/233847 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networksbag-of-samplingsbiometricsconvolutional neural networkshandwritten dynamicsperson identificationBiometric recognition provides straightforward methods to deal with the problem of identifying people under certain circumstances. Additionally, a well-calibrated biometric system enhances security policies and prevents malicious attempts, such as fraud or identity theft. Deep learning has arisen to foster the problem by extracting high-level features that compose the so-called ‘user fingerprint’, that is, digital identification of a particular individual. Nevertheless, personal identification is not a trivial task, as many traits might define an individual, varying according to the task's domain. An exciting way to overcome such a problem is to employ handwritten dynamics, which are hand- and motor-based signals from an individual's writing style and obtained through a biometric smartpen. In this work, we propose using such signals to identify an individual through convolutional neural networks. Essentially, the proposed work uses a neighbour-based bag-of-samplings procedure to sample the signals to a fixed size and feeds them into a neural network responsible for extracting their features and further classifying them. The experiments were conducted over two handwritten dynamic datasets, NewHandPD and SignRec, and established new fruitful state-of-the-art concerning these particular datasets and the corresponding context.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Department of Computing São Paulo State UniversityAv. Eng. Luís Edmundo Carrijo Coube 14-01 Vargem Limpa, SPDepartment of Computing São Paulo State UniversityFAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2019/02205-5FAPESP: 2019/07665-4FAPESP: 2020/12101-0CNPq: 307066/2017-7CNPq: 427968/2018-6Universidade Estadual Paulista (UNESP)Vargem Limpade Rosa, Gustavo H. [UNESP]Roder, Mateus [UNESP]Papa, João P. [UNESP]2022-05-01T11:07:18Z2022-05-01T11:07:18Z2022-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1111/exsy.12891Expert Systems, v. 39, n. 4, 2022.1468-03940266-4720http://hdl.handle.net/11449/23384710.1111/exsy.128912-s2.0-85120072404Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengExpert Systemsinfo:eu-repo/semantics/openAccess2024-04-23T16:10:43Zoai:repositorio.unesp.br:11449/233847Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:10:43Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
title |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
spellingShingle |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks de Rosa, Gustavo H. [UNESP] bag-of-samplings biometrics convolutional neural networks handwritten dynamics person identification |
title_short |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
title_full |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
title_fullStr |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
title_full_unstemmed |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
title_sort |
Neighbour-based bag-of-samplings for person identification through handwritten dynamics and convolutional neural networks |
author |
de Rosa, Gustavo H. [UNESP] |
author_facet |
de Rosa, Gustavo H. [UNESP] Roder, Mateus [UNESP] Papa, João P. [UNESP] |
author_role |
author |
author2 |
Roder, Mateus [UNESP] Papa, João P. [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Vargem Limpa |
dc.contributor.author.fl_str_mv |
de Rosa, Gustavo H. [UNESP] Roder, Mateus [UNESP] Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
bag-of-samplings biometrics convolutional neural networks handwritten dynamics person identification |
topic |
bag-of-samplings biometrics convolutional neural networks handwritten dynamics person identification |
description |
Biometric recognition provides straightforward methods to deal with the problem of identifying people under certain circumstances. Additionally, a well-calibrated biometric system enhances security policies and prevents malicious attempts, such as fraud or identity theft. Deep learning has arisen to foster the problem by extracting high-level features that compose the so-called ‘user fingerprint’, that is, digital identification of a particular individual. Nevertheless, personal identification is not a trivial task, as many traits might define an individual, varying according to the task's domain. An exciting way to overcome such a problem is to employ handwritten dynamics, which are hand- and motor-based signals from an individual's writing style and obtained through a biometric smartpen. In this work, we propose using such signals to identify an individual through convolutional neural networks. Essentially, the proposed work uses a neighbour-based bag-of-samplings procedure to sample the signals to a fixed size and feeds them into a neural network responsible for extracting their features and further classifying them. The experiments were conducted over two handwritten dynamic datasets, NewHandPD and SignRec, and established new fruitful state-of-the-art concerning these particular datasets and the corresponding context. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-05-01T11:07:18Z 2022-05-01T11:07:18Z 2022-05-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1111/exsy.12891 Expert Systems, v. 39, n. 4, 2022. 1468-0394 0266-4720 http://hdl.handle.net/11449/233847 10.1111/exsy.12891 2-s2.0-85120072404 |
url |
http://dx.doi.org/10.1111/exsy.12891 http://hdl.handle.net/11449/233847 |
identifier_str_mv |
Expert Systems, v. 39, n. 4, 2022. 1468-0394 0266-4720 10.1111/exsy.12891 2-s2.0-85120072404 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Expert Systems |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799964504896831488 |