Finger-vein individuals identification on massive databases

In massive biometric identification, response times highlydepend on the searching algorithms. Traditional systems operate with databases of up to 10,000 records. In large databases, with an increasing number of simultaneous queries, the system response time is a critical factor. This work proposes a...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Guidet, Sebastián, Barrientos, Ricardo J., Frati, Fernando Emmanuel, Hernández-García, Ruber
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2020
Materias:
Ciencias Informáticas
High Performance Computing
Identification of individuals
Local linear binary pattern
Finger veins
GPU
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/104768
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-104768
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
High Performance Computing
Identification of individuals
Local linear binary pattern
Finger veins
GPU
spellingShingle Ciencias Informáticas
High Performance Computing
Identification of individuals
Local linear binary pattern
Finger veins
GPU
Guidet, Sebastián
Barrientos, Ricardo J.
Frati, Fernando Emmanuel
Hernández-García, Ruber
Finger-vein individuals identification on massive databases
topic_facet Ciencias Informáticas
High Performance Computing
Identification of individuals
Local linear binary pattern
Finger veins
GPU
description In massive biometric identification, response times highlydepend on the searching algorithms. Traditional systems operate with databases of up to 10,000 records. In large databases, with an increasing number of simultaneous queries, the system response time is a critical factor. This work proposes a GPU-based implementation for the matching process of finger-vein massive identification. Experimental resultss how that our approach solves up to 256 simultaneous queries on large databases achieving up to 136x.
format Objeto de conferencia
Objeto de conferencia
author Guidet, Sebastián
Barrientos, Ricardo J.
Frati, Fernando Emmanuel
Hernández-García, Ruber
author_facet Guidet, Sebastián
Barrientos, Ricardo J.
Frati, Fernando Emmanuel
Hernández-García, Ruber
author_sort Guidet, Sebastián
title Finger-vein individuals identification on massive databases
title_short Finger-vein individuals identification on massive databases
title_full Finger-vein individuals identification on massive databases
title_fullStr Finger-vein individuals identification on massive databases
title_full_unstemmed Finger-vein individuals identification on massive databases
title_sort finger-vein individuals identification on massive databases
publishDate 2020
url http://sedici.unlp.edu.ar/handle/10915/104768
work_keys_str_mv AT guidetsebastian fingerveinindividualsidentificationonmassivedatabases
AT barrientosricardoj fingerveinindividualsidentificationonmassivedatabases
AT fratifernandoemmanuel fingerveinindividualsidentificationonmassivedatabases
AT hernandezgarciaruber fingerveinindividualsidentificationonmassivedatabases
bdutipo_str Repositorios
_version_ 1764820442339606529

Ejemplares similares