Publication

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications

Chaves, D., Fidalgo, E., Alegre, E., Alaiz-Rodriguez, R., Janez-Martino, F. & Azzopardi, G., 11-Aug-2020, In : Sensors. 20, 16, p. 1-21 21 p., 4491.

Research output: Contribution to journalArticleAcademicpeer-review

  • Deisy Chaves
  • Eduardo Fidalgo
  • Enrique Alegre
  • Rocio Alaiz-Rodriguez
  • Francisco Janez-Martino
  • George Azzopardi

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to50%of the original size in GPUs and images resized to25%of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113, which is very promising for the forensic field.

Original languageEnglish
Article number4491
Pages (from-to)1-21
Number of pages21
JournalSensors
Volume20
Issue number16
Publication statusPublished - 11-Aug-2020

    Keywords

  • face detection, CSEM, deep learning, GPU, CPU, Benchmark, regression, REAL-TIME, RECOGNITION

Download statistics

No data available

ID: 131691147