Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/1946
Title: Towards Automatic Detection of Child Pornography
Authors: Sae-Bae, Napa
Sun, Xiaoxi
Sencar, Hüsrev Taha
Memon, Nasir D.
143687
Keywords: Image processing
Statistical tests
Age classification
Automatic Detection
Child pornographies
Digital image
Facial feature
Image detection systems
Skin color filter
True positive rates
Issue Date: 2014
Publisher: IEEE
Source: Sae-Bae, N., Sun, X., Sencar, H. T., & Memon, N. D. (2014, October). Towards automatic detection of child pornography. In 2014 IEEE International Conference on Image Processing (ICIP)(pp. 5332-5336). IEEE.
Abstract: This paper presents a child pornographic image detection system that identifies human skin tones in digital images, extracts features to detect explicit images and performs facial image based age classification. The novelty of the technique relies on the use of a robust and very fast skin color filter and a new set of facial features for improved identification of child faces. Tests on a dataset containing explicit images taken under different illuminations and reflecting a diversity of human skin tones, show that explicit images can be differentiated from benign images with around 90% accuracy. Similarly, tests performed on adult and child facial images yielded an accuracy of 80% in detecting child faces. Test conducted on 105 images involving semi-naked children (with no sexual context) revealed that the system has true positive rates of 83% in detecting explicit-like images and 96.5% in detecting child faces.
URI: https://ieeexplore.ieee.org/document/7026079
https://hdl.handle.net/20.500.11851/1946
ISBN: 978-1-4799-5751-4
ISSN: 1522-4880
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender

SCOPUSTM   
Citations

26
checked on Sep 23, 2022

Page view(s)

20
checked on Dec 26, 2022

Google ScholarTM

Check

Altmetric


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