Development of a Hardware Benchmark for Forensic Face Detection Applications

J Velasco-Mata, Deisy Chaves, V de Mata, M. W. Al-Nabki, Eduardo Fidalgo, Enrique Alegre, George Azzopardi

Onderzoeksoutput: Conference contributionAcademicpeer review

102 Downloads (Pure)

Samenvatting

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.
Originele taal-2English
TitelInvestigación en Ciberseguridad Actas de las VI Jornadas Nacionales
RedacteurenManuel A. Serrano
UitgeverijEdiciones de la Universidad de Castilla-La Mancha
Pagina's129-130
Aantal pagina's2
ISBN van geprinte versie978-84-9044-463-4
DOI's
StatusPublished - jun.-2021
EvenementCybersecurity Research National Conferences - INCIBE, Leon, Spain
Duur: 10-jun.-202111-jun.-2021

Publicatie series

NaamInvestigación en Ciberseguridad. Jornadas Nacionales de Investigación en Ciberseguridad
Volume34

Conference

ConferenceCybersecurity Research National Conferences
Verkorte titelJNIC
Land/RegioSpain
StadLeon
Periode10/06/202111/06/2021

Vingerafdruk

Duik in de onderzoeksthema's van 'Development of a Hardware Benchmark for Forensic Face Detection Applications'. Samen vormen ze een unieke vingerafdruk.

Citeer dit