Evaluation of local descriptors and CNNs for non-adult detection in visual content

•Age estimation for CAM detection is proposed.•Design of a challenging adult/non-adult benchmark.•Evaluation of local descriptors and CNNs.•Both focuses report accuracies about 87–88%.•Local descriptors and CNNs score level fusion reaches 93%. The recent evolution of storage devices, digital embedde...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters 2018-10, Vol.113, p.10-18
Main Authors: Castrillón-Santana, Modesto, Lorenzo-Navarro, Javier, Travieso-González, Carlos M., Freire-Obregón, David, Alonso-Hernández, Jesús B.
Format: Article
Language:English
Subjects:
Adults
Age estimation
Artificial neural networks
Cameras
Child abuse & neglect
CNNs
Content management
Datasets
Local descriptors
Neural networks
Predators
Score level fusion
Social networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Age estimation for CAM detection is proposed.•Design of a challenging adult/non-adult benchmark.•Evaluation of local descriptors and CNNs.•Both focuses report accuracies about 87–88%.•Local descriptors and CNNs score level fusion reaches 93%. 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%.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2017.03.016