Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/42117
Title: Evaluation of local descriptors and CNNs for non-adult detection in visual content
Authors: Castrillón-Santana, Modesto 
Lorenzo-Navarro, Javier 
Travieso-González, Carlos M. 
Freire-Obregón, David 
Alonso-Hernández, Jesús B. 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: MSC: 41A05
MSC: 41A10
MSC: 65D05
MSC: 65D17
Age estimation, et al
Issue Date: 2018
Project: TIN2015-64395-R
Journal: Pattern Recognition Letters 
Abstract: The recent evolution of storage devices, digital embedded cameras and the Internet have collaterally allowed sexual predators to take advantage of these technological breakthroughs to gather illegal media, which is exhibited uncensored through Peer-to-Peer file sharing networks. In this paper, we are particularly concerned about the increasing availability of Child Abuse Material. Therefore, we have explored alternatives to detect non-adults in visual content. Initially, different age estimations and underage detection techniques are reviewed by analyzing existing datasets. Finally, several local descriptors and Convolutional Neural Networks for underage detection are evaluated. The experimental results obtained for a large dataset that combines collections such as FG-Net, Adience, GenderChildren, The Image of Groups and Boys2Men evidence the complementary information contained in both local descriptors and neural networks, as their fusion boosts the accuracy of non-adult detection to over 93%.
URI: http://hdl.handle.net/10553/42117
ISSN: 0167-8655
DOI: 10.1016/j.patrec.2017.03.016
Source: Pattern Recognition Letters [ISSN 0167-8655], v. 113, p. 10-18
Appears in Collections:Artículos
Preprint
Unknown (613,97 kB)
Show full item record

SCOPUSTM   
Citations

8
checked on Dec 1, 2024

WEB OF SCIENCETM
Citations

9
checked on Nov 24, 2024

Page view(s)

221
checked on Nov 9, 2024

Download(s)

57
checked on Nov 9, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.