28 Development of a Hardware Benchmark for Forensic Face Detection Applications

Face detection techniques are valuable in the forensic investigation since they help criminal investigators to identify victims/offenders in child sexual exploitation material. Deep learning approaches proved successful in these tasks, but their high computational requirements make them unsuitable i...

Descripción completa

Detalles Bibliográficos
Autores: Velasco Mata, Javier, Chaves, Deisy, Mata, Verónica de, Al-Nabki, Mhd Wesam, Fidalgo, Eduardo, Alegre, Enrique, Azzopardi, George
Tipo de recurso: capítulo de libro
Fecha de publicación:2021
País:España
Institución:Universidad de Castilla-La Mancha
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/28635
Acceso en línea:http://doi.org/10.18239/jornadas_2021.34.28
http://hdl.handle.net/10578/28635
Access Level:acceso abierto
Palabra clave:Face Detection
Benchmark
GPU
CPU
id ES_fb1240468bb12743dff4979826a5d2d0
oai_identifier_str oai:ruidera.uclm.es:10578/28635
network_acronym_str ES
network_name_str España
repository_id_str
spelling 28 Development of a Hardware Benchmark for Forensic Face Detection ApplicationsVelasco Mata, JavierChaves, DeisyMata, Verónica deAl-Nabki, Mhd WesamFidalgo, EduardoAlegre, EnriqueAzzopardi, GeorgeFace DetectionBenchmarkGPUCPUFace detection techniques are valuable in the forensic investigation since they help criminal investigators to identify victims/offenders in child sexual exploitation material. Deep learning approaches proved successful in these tasks, but their high computational requirements make them unsuitable if there are time constraints. To cope with this problem, we use a resizing strategy over three face detection techniques —MTCNN, PyramidBox and DSFD— to improve their speed over samples selected from the WIDER Face and UFDD datasets across several CPUs and GPUs. The best speed-detection trade-off was achieved reducing the images to 50% of their original size and then applying DSFD. The fastest hardware for this purpose was a Nvidia GPU based on the Turing architecture.Ediciones de la Universidad de Castilla-La Mancha202120212021info:eu-repo/semantics/bookPartapplication/pdfapplication/pdfhttp://doi.org/10.18239/jornadas_2021.34.28http://hdl.handle.net/10578/28635reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Universidad de Castilla-La ManchaInglésinfo:eu-repo/semantics/openAccessoai:ruidera.uclm.es:10578/286352026-05-27T07:36:41Z
dc.title.none.fl_str_mv 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
title 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
spellingShingle 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
Velasco Mata, Javier
Face Detection
Benchmark
GPU
CPU
title_short 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
title_full 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
title_fullStr 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
title_full_unstemmed 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
title_sort 28 Development of a Hardware Benchmark for Forensic Face Detection Applications
dc.creator.none.fl_str_mv Velasco Mata, Javier
Chaves, Deisy
Mata, Verónica de
Al-Nabki, Mhd Wesam
Fidalgo, Eduardo
Alegre, Enrique
Azzopardi, George
author Velasco Mata, Javier
author_facet Velasco Mata, Javier
Chaves, Deisy
Mata, Verónica de
Al-Nabki, Mhd Wesam
Fidalgo, Eduardo
Alegre, Enrique
Azzopardi, George
author_role author
author2 Chaves, Deisy
Mata, Verónica de
Al-Nabki, Mhd Wesam
Fidalgo, Eduardo
Alegre, Enrique
Azzopardi, George
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Face Detection
Benchmark
GPU
CPU
topic Face Detection
Benchmark
GPU
CPU
description Face detection techniques are valuable in the forensic investigation since they help criminal investigators to identify victims/offenders in child sexual exploitation material. Deep learning approaches proved successful in these tasks, but their high computational requirements make them unsuitable if there are time constraints. To cope with this problem, we use a resizing strategy over three face detection techniques —MTCNN, PyramidBox and DSFD— to improve their speed over samples selected from the WIDER Face and UFDD datasets across several CPUs and GPUs. The best speed-detection trade-off was achieved reducing the images to 50% of their original size and then applying DSFD. The fastest hardware for this purpose was a Nvidia GPU based on the Turing architecture.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv http://doi.org/10.18239/jornadas_2021.34.28
http://hdl.handle.net/10578/28635
url http://doi.org/10.18239/jornadas_2021.34.28
http://hdl.handle.net/10578/28635
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Ediciones de la Universidad de Castilla-La Mancha
publisher.none.fl_str_mv Ediciones de la Universidad de Castilla-La Mancha
dc.source.none.fl_str_mv reponame:RUIdeRA. Repositorio Institucional de la UCLM
instname:Universidad de Castilla-La Mancha
instname_str Universidad de Castilla-La Mancha
reponame_str RUIdeRA. Repositorio Institucional de la UCLM
collection RUIdeRA. Repositorio Institucional de la UCLM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425295312814080
score 15,300719

Similares en LA Referencia