Experiences accelerating features selection in Viola-Jones algorithm

Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not appropriat...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Lescano, Germán Ezequiel, Santana Mansilla, Pablo, Costaguta, Rosanna
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2016
Materias:
Ciencias Informáticas
Adaboost
Viola-Jones algorithm
CUDA
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/55806
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-55806
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
Adaboost
Viola-Jones algorithm
CUDA
spellingShingle Ciencias Informáticas
Adaboost
Viola-Jones algorithm
CUDA
Lescano, Germán Ezequiel
Santana Mansilla, Pablo
Costaguta, Rosanna
Experiences accelerating features selection in Viola-Jones algorithm
topic_facet Ciencias Informáticas
Adaboost
Viola-Jones algorithm
CUDA
description Faces and facial expressions recognition is an interesting topic for researchers in machine vision. Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not appropriately optimized. In this study, several settings for implementing the training phase are analyzed. The aim was to share our experiences when we try to accelerate the training phase using one computer with a graphical processing unit (GPU). For each setting, the execution times were analyzed and compared with previous studies. Although we don't contribute to break new ground in topic or methodology, we decide to share our experience in order to show an antecedent working with a cheap GPU with the aim that this can be useful to another for to make comparisons.
format Objeto de conferencia
Objeto de conferencia
author Lescano, Germán Ezequiel
Santana Mansilla, Pablo
Costaguta, Rosanna
author_facet Lescano, Germán Ezequiel
Santana Mansilla, Pablo
Costaguta, Rosanna
author_sort Lescano, Germán Ezequiel
title Experiences accelerating features selection in Viola-Jones algorithm
title_short Experiences accelerating features selection in Viola-Jones algorithm
title_full Experiences accelerating features selection in Viola-Jones algorithm
title_fullStr Experiences accelerating features selection in Viola-Jones algorithm
title_full_unstemmed Experiences accelerating features selection in Viola-Jones algorithm
title_sort experiences accelerating features selection in viola-jones algorithm
publishDate 2016
url http://sedici.unlp.edu.ar/handle/10915/55806
work_keys_str_mv AT lescanogermanezequiel experiencesacceleratingfeaturesselectioninviolajonesalgorithm
AT santanamansillapablo experiencesacceleratingfeaturesselectioninviolajonesalgorithm
AT costagutarosanna experiencesacceleratingfeaturesselectioninviolajonesalgorithm
bdutipo_str Repositorios
_version_ 1764820477448028160

Ejemplares similares