Automated Detection of Violent Contents for Film Censorship using Deep Learning

Citation

Abdullah, Muhammad Shahril Nizam and Abdul Karim, Hezerul and AlDahoul, Nouar (2022) Automated Detection of Violent Contents for Film Censorship using Deep Learning. PIARTI. pp. 1-2. (Unpublished)

[img] Text
MMUPaper4 SASSP IPIARTI 2022 Muhammad Shahril Nizam.pdf
Restricted to Repository staff only

Download (392kB)

Abstract

Nowadays, we are facing through the rapid advancement of technologies, which includes the development of Artificial Intelligence in our daily lives. This research proposes a combination of Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to perform sequence frame prediction. The videos are converted into frames and its features are being extracted using the pre-trained CNN. Training is conducted using the arbitrarily-defined RNN model to provide the binary classification of whether a video contains violence scene or vice versa. The models are trained, validated, and tested using a total of four thousand (4000) videos taken from online source.

Item Type: Article
Uncontrolled Keywords: Convolutional Neural Network, Neural Networks
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions: Faculty of Engineering (FOE)
Depositing User: Dr. Sarina Mansor
Date Deposited: 24 Nov 2022 02:30
Last Modified: 22 Mar 2023 05:01
URII: http://shdl.mmu.edu.my/id/eprint/10662

Downloads

Downloads per month over past year

View ItemEdit (login required)