Open AccessAutomated Nudity Recognition using Very Deep Residual Learning Network
Author(s) -
Rasoul Banaeeyan,
Hezerul Abdul Karim,
Muhammad Abdullah,
Mohammad Faizal Ahmad Fauzi,
Sarina Mansor,
John See
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.c1024.1083s19
Subject(s) - artificial intelligence , residual neural network , convolutional neural network , computer science , residual , deep learning , machine learning , term (time) , leverage (statistics) , transfer of learning , process (computing) , the internet , artificial neural network , world wide web , algorithm , physics , quantum mechanics , operating system
The exponentially growing number of pornographic material has brought many challenges to the modern daily life, particularly where children and minors have unlimited access to the internet. In Malaysia, all local and foreign films should obtain the suitability approval before distribution or public viewing, and this process of screening visual contents of all the TV channels imposes a huge censorship cost to the service providers such as Unifi TV. To leverage this issue, this paper proposes to use an emerging model of Deep Learning (DL) techniques called Residual Learning Convolutional Neural Networks (ResNet), in order to automate the process of nudity detection in visual contents. The pre-trained ResNet model, with hundred and one layers, was utilized to perform transfer learning and solve a new binary classification problem of nudity versus non-nudity. The performance of the proposed model is evaluated based on a newly created dataset comprising more than 4k samples of nudity and non-nudity images. After conducting experiments on the nudity dataset, the deep learning method succeeded to achieve the best performance of 70.42% in term of F-score, 84.04% in term of accuracy, and 93.72% in term of AUC .