Digital forensics experts are increasingly confronted with investigating large amounts of data and judging if it contains digital contraband. In this paper, we present an adaptable solution for detecting nudity or pornography in color images. We combine a novel skin detection approach with machine learning techniques to alleviate manual image screening. We upgrade previous approaches by leveraging machine learning and introducing several novel methods to enhance detection rates. Our nudity assessment uses skin detection and positioning of skin areas within a picture. Sizes, shapes and placements of detected skin regions as well as the total amount of skin in an image are used as features for a support vector machine that finally classifies the image as non-pornographic or pornographic. With a recall of 65.7% and 6.4% false positive rate, our approach outperforms the best reported detection approaches.
@inproceedings{Platzer2014Skin_Sheriff,
title = {{Skin Sheriff: A Machine Learning Solution for Detecting Explicit Images}},
author = {Platzer, Christian and Stuetz, Martin and Lindorfer, Martina},
booktitle = {Proceedings of the 2nd International Workshop on Security and Forensics in Communication Systems},
series = {ASIACCS-SFCS},
month = {June},
year = {2014},
address = {Kyoto, Japan}
}