Enhancing classification structures for biometrics applications /

The effectiveness with which individual identity can be predicted in different scenarios can benefit from seeking a broad base of identity evidence. Many approaches to the implementation of biometric-based identification systems are possible, and different configurations are likely to generate signi...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Principais autores: Abreu, Márjory Cristiany da Costa., Fairhurst, Michael C., University of Kent.
Formato: Tese
Publicado em:
Assuntos:
Biometria -
Identificação biométrica -
Estrutura -
Classificação -
Implementação -
Estratégias -
Abordagem -
Design -
Endereço do item:https://app.bczm.ufrn.br/home/#/item/234889
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
id oai:localhost:123456789-157244
record_format dspace
spelling oai:localhost:123456789-1572442022-10-06T15:55:42Z Enhancing classification structures for biometrics applications / Abreu, Márjory Cristiany da Costa. Fairhurst, Michael C., University of Kent. Biometria - Identificação biométrica - Estrutura - Classificação - Implementação - Estratégias - Abordagem - Design - The effectiveness with which individual identity can be predicted in different scenarios can benefit from seeking a broad base of identity evidence. Many approaches to the implementation of biometric-based identification systems are possible, and different configurations are likely to generate significantly different operational characteristics. The choice of implementational structure is therefore very dependent on the performance criteria which are most important in any particular task scenario. The issue of improving performance can be addressed in a number of ways, but system configurations based on integrating different in formation sources are a widely adopted means of achieving this. In this thesis, we will evaluate the merits of using very different classification structures, and we will investigate how fundamentally different strategies for implementation can increase the degree of choice available in achieving particular performance criteria. In particular, we propose that the design process could be carried out using three different approaches: multicategory, multiclassifier and multimodal. In the multimodal approach, we will show a new way to improve identification performance, where both direct biometric samples and "soft-biometric" knowledge are combined. In the multiclassifier approach, we will illustrate the merits of an implementation based on a multiagent computational architecture. And finally, in the multimodal approach, we will investigate the benefits of correctly choosing the modalities for a multimodal system using handwritten signature as a case study, more specifically presenting some qualitative analysis as support. The contributions presented in this work are very encouraging and point to new and more flexible paradigms for designing s^-stems based on biometrics. 1 2022-10-06T15:55:42Z 2022-10-06T15:55:42Z 2010. Tese 004.056.523 A162e TESE 234889 https://app.bczm.ufrn.br/home/#/item/234889 https://app.bczm.ufrn.br/home/#/item/234889
institution Acervo SISBI
collection SIGAA
topic Biometria -
Identificação biométrica -
Estrutura -
Classificação -
Implementação -
Estratégias -
Abordagem -
Design -
spellingShingle Biometria -
Identificação biométrica -
Estrutura -
Classificação -
Implementação -
Estratégias -
Abordagem -
Design -
Abreu, Márjory Cristiany da Costa.
Fairhurst, Michael C.,
University of Kent.
Enhancing classification structures for biometrics applications /
description The effectiveness with which individual identity can be predicted in different scenarios can benefit from seeking a broad base of identity evidence. Many approaches to the implementation of biometric-based identification systems are possible, and different configurations are likely to generate significantly different operational characteristics. The choice of implementational structure is therefore very dependent on the performance criteria which are most important in any particular task scenario. The issue of improving performance can be addressed in a number of ways, but system configurations based on integrating different in formation sources are a widely adopted means of achieving this. In this thesis, we will evaluate the merits of using very different classification structures, and we will investigate how fundamentally different strategies for implementation can increase the degree of choice available in achieving particular performance criteria. In particular, we propose that the design process could be carried out using three different approaches: multicategory, multiclassifier and multimodal. In the multimodal approach, we will show a new way to improve identification performance, where both direct biometric samples and "soft-biometric" knowledge are combined. In the multiclassifier approach, we will illustrate the merits of an implementation based on a multiagent computational architecture. And finally, in the multimodal approach, we will investigate the benefits of correctly choosing the modalities for a multimodal system using handwritten signature as a case study, more specifically presenting some qualitative analysis as support. The contributions presented in this work are very encouraging and point to new and more flexible paradigms for designing s^-stems based on biometrics.
format Tese
author Abreu, Márjory Cristiany da Costa.
Fairhurst, Michael C.,
University of Kent.
author_facet Abreu, Márjory Cristiany da Costa.
Fairhurst, Michael C.,
University of Kent.
author_sort Abreu, Márjory Cristiany da Costa.
title Enhancing classification structures for biometrics applications /
title_short Enhancing classification structures for biometrics applications /
title_full Enhancing classification structures for biometrics applications /
title_fullStr Enhancing classification structures for biometrics applications /
title_full_unstemmed Enhancing classification structures for biometrics applications /
title_sort enhancing classification structures for biometrics applications /
publishDate 2022
url https://app.bczm.ufrn.br/home/#/item/234889
work_keys_str_mv AT abreumarjorycristianydacosta enhancingclassificationstructuresforbiometricsapplications
AT fairhurstmichaelc enhancingclassificationstructuresforbiometricsapplications
AT universityofkent enhancingclassificationstructuresforbiometricsapplications
_version_ 1766835775329009664

Registros relacionados