An Evaluation of Traditional and CNN-based Feature Descriptors for Cartoon Pornography Detection

Citation

AlDahoul, Nouar and Abdul Karim, Hezerul and Lye Abdullah, Mohd Haris and Ba Wazir, Abdulaziz Saleh and Ahmad Fauzi, Mohammad Faizal and Tan, Myles Joshua Toledo and Mansor, Sarina and Hor, Sui Lyn (2021) An Evaluation of Traditional and CNN-based Feature Descriptors for Cartoon Pornography Detection. IEEE Access, 9. pp. 39910-39925. ISSN 2169-3536

[img] Text
An Evaluation of Traditional and CNN-Based Feature Descriptors for Cartoon Pornography Detection.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

Inappropriate visual content on the internet has spread everywhere, and thus children are exposed unintentionally to sexually explicit visual content. Animated cartoon movies sometimes have sensitive content such as pornography and sex. Usually, video sharing platforms take children’s e-safety into consideration through manual censorship, which is both time-consuming and expensive. Therefore, automated cartoon censorship is highly recommended to be integrated into media platforms. In this paper, various methods and approaches were explored to detect inappropriate visual content in cartoon animation. First, state-of-the-art conventional feature techniques were utilised and evaluated. In addition, a simple end-to-end convolutional neural network (CNN) was used and was found to outperform conventional techniques in terms of accuracy (85.33%) and F1 score (83.46%). Additionally, to target the deeper version of CNNs, ResNet, and EfficientNet were demonstrated and compared. The CNN-based extracted features were mapped into two classes: normal and porn. To improve the model’s performance, we utilised feature and decision fusion approaches which were found to outperform state-of-the-art techniques in terms of accuracy (87.87%), F1 score (87.87%), and AUC (94.40%). To validate the domain generalisation performance of the proposed methods, CNNs, pre-trained on the cartoon dataset were evaluated on public NPDI-800 natural videos and found to provide an accuracy of 79.92%, and F1 score of 80.58%. Similarly, CNNs, pre-trained on the public NPDI-800 natural videos, were evaluated on cartoon dataset and found to give an accuracy of 82.666%, and F1 score of 81.588%. Finally, a novel cartoon pornography dataset, with various characters, skin colours, positions, viewpoints, and scales, was proposed.

Item Type: Article
Uncontrolled Keywords: Transfer learning (Machine learning)
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 08 May 2021 16:01
Last Modified: 08 May 2021 16:01
URII: http://shdl.mmu.edu.my/id/eprint/8689

Downloads

Downloads per month over past year

View ItemEdit (login required)