Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/112746
Title: | Detecting and ranking pornographic content in videos |
Authors: | Borg, Mark Tabone, Andre Bonnici, Alexandra Cristina, Stefania Farrugia, Reuben A. Camilleri, Kenneth P. |
Keywords: | Internet pornography Internet pornography -- Prevention Deep learning (Machine learning) Digital forensic science |
Issue Date: | 2022 |
Publisher: | Elsevier |
Citation: | Borg, M., Tabone, A., Bonnici, A., Cristina, S., Farrugia, R. A. & Camilleri, K. P. (2022). Detecting and ranking pornographic content in videos. Forensic Science International: Digital Investigation, 42-43, 301436. |
Abstract: | The detection and ranking of pornographic material is a challenging task, especially when it comes to videos, due to factors such as the definition of what is pornographic and its severity level, the volumes of data that need to be processed, as well as temporal ambiguities between the benign and pornographic portions of a video. In this paper we propose a video-based pornographic detection system consisting of a convolutional neural network (CNN) for automatic feature extraction, followed by a recurrent neural network (RNN) in order to exploit the temporal information present in videos. We describe how our system can be used for both video-level labelling as well as for localising pornographic content within videos. Given porno- graphic video segments, we describe an efficient method for finding sexual objects within the segments, and how the types of detected sexual objects can be used to generate an estimate of the severity (‘harmfulness’) of the pornographic content. This estimate is then utilised for ranking videos based on their severity, a common requirement of law enforcement agencies (LEAs) when it comes to categorising pornographic content. We evaluate our proposed system against a benchmark dataset, achieving results on par with the state of the art, while providing additional benefits such as ranking videos according to their severity level, something which to the best of our knowledge has not been attempted before. We perform further investigations into model generalisability by performing an out-of-distribution (o.o.d.) test, investigate whether our model is making use of shortcut learning, and address the issue of explainability. The results obtained indicate that our model is using strong learning, thus further validating our proposed approach and the results obtained. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/112746 |
Appears in Collections: | Scholarly Works - FacEngSCE |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Detecting and ranking pornographic content in videos.pdf | 4.11 MB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.