Private Body Part Detection using Deep Learning

André Tabone, Alexandra Bonnici, Stefania Cristina, Reuben Farrugia, Kenneth Camilleri

2020

Abstract

Fast and accurate detection of sexually exploitative imagery is necessary for law enforcement agencies to allow for prosecution of suspect individuals. In literature, techniques which can be used to assist law enforcement agencies only determine whether the image content is pornographic or benign. In this paper, we provide a review on classical handcrafted-feature based and deep-learning based pornographic detection in images and describe a framework which goes beyond this, to identify the location of genitalia in the image. Despite this being a computationally complex task, we show that by learning multiple features, a MobileNet framework can achieve an accuracy of 76.29% in the correct labelling of female and male sexual organs.

Paper Citation

in Harvard Style

Tabone A., Bonnici A., Cristina S., Farrugia R. and Camilleri K. (2020). Private Body Part Detection using Deep Learning. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 205-211. DOI: 10.5220/0009101502050211

in Bibtex Style

@conference{icpram20,
author={André Tabone and Alexandra Bonnici and Stefania Cristina and Reuben Farrugia and Kenneth Camilleri},
title={Private Body Part Detection using Deep Learning},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={205-211},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009101502050211},
isbn={978-989-758-397-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Private Body Part Detection using Deep Learning
SN - 978-989-758-397-1
AU - Tabone A.
AU - Bonnici A.
AU - Cristina S.
AU - Farrugia R.
AU - Camilleri K.
PY - 2020
SP - 205
EP - 211
DO - 10.5220/0009101502050211