Staff View: An improvised CNN model for fake image detection

An improvised CNN model for fake image detection

The last decade has witnessed a multifold growth of image data courtesy of the emergence of social networking services like Facebook, Instagram, LinkedIn etc. The major menace faced by today’s world is the issue of doctored images, where-in the photographs are altered using a rich set of ways like s...

Full description

Saved in:

Bibliographic Details
Main Authors:	Hamid, Yasir, Elyassami, Sanaa, Gulzar, Yonis, Balasaraswathi, Veeran Ranganathan, Habuza, Tetiana, Wani, Sharyar
Format:	Article
Language:	English
Published:	Springer Nature 2022
Subjects:	QA75 Electronic computers. Computer science TK7885 Computer engineering
Online Access:	http://irep.iium.edu.my/101720/1/Screen%20Shot%202022-12-07%20at%208.23.03%20AM.png http://irep.iium.edu.my/101720/ https://link.springer.com/article/10.1007/s41870-022-01130-5
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.iium.irep.101720
record_format	dspace
spelling	my.iium.irep.1017202022-12-07T05:49:49Z http://irep.iium.edu.my/101720/ An improvised CNN model for fake image detection Hamid, Yasir Elyassami, Sanaa Gulzar, Yonis Balasaraswathi, Veeran Ranganathan Habuza, Tetiana Wani, Sharyar QA75 Electronic computers. Computer science TK7885 Computer engineering The last decade has witnessed a multifold growth of image data courtesy of the emergence of social networking services like Facebook, Instagram, LinkedIn etc. The major menace faced by today’s world is the issue of doctored images, where-in the photographs are altered using a rich set of ways like splicing, copy-move, removal to change their meaning and hence demands serious mitigation mechanisms to be thought of. The problem when seen from the prism of Artificial intelligence is a binary classification one, where-in the characterization must be drawn between the original and the manipulated images. This research work proposes a computer vision model based on Convolution Neural Networks for fake image detection. A comparative analysis of 6 popular traditional machine learning models and 6 different CNN architectures to select the best possible model for further experimentation. The proposed model based on ResNet50 employed with powerful preprocessing techniques results in a perfect fake image detector having a total accuracy of 0.99 having an improvement of around 18% performance with other models. Springer Nature 2022-11-16 Article PeerReviewed application/pdf en http://irep.iium.edu.my/101720/1/Screen%20Shot%202022-12-07%20at%208.23.03%20AM.png Hamid, Yasir and Elyassami, Sanaa and Gulzar, Yonis and Balasaraswathi, Veeran Ranganathan and Habuza, Tetiana and Wani, Sharyar (2022) An improvised CNN model for fake image detection. International Journal of Information Technology. ISSN 2511-2104 E-ISSN 2511-2112 (In Press) https://link.springer.com/article/10.1007/s41870-022-01130-5 10.1007/s41870-022-01130-5
institution	Universiti Islam Antarabangsa Malaysia
building	IIUM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	International Islamic University Malaysia
content_source	IIUM Repository (IREP)
url_provider	http://irep.iium.edu.my/
language	English
topic	QA75 Electronic computers. Computer science TK7885 Computer engineering
spellingShingle	QA75 Electronic computers. Computer science TK7885 Computer engineering Hamid, Yasir Elyassami, Sanaa Gulzar, Yonis Balasaraswathi, Veeran Ranganathan Habuza, Tetiana Wani, Sharyar An improvised CNN model for fake image detection
description	The last decade has witnessed a multifold growth of image data courtesy of the emergence of social networking services like Facebook, Instagram, LinkedIn etc. The major menace faced by today’s world is the issue of doctored images, where-in the photographs are altered using a rich set of ways like splicing, copy-move, removal to change their meaning and hence demands serious mitigation mechanisms to be thought of. The problem when seen from the prism of Artificial intelligence is a binary classification one, where-in the characterization must be drawn between the original and the manipulated images. This research work proposes a computer vision model based on Convolution Neural Networks for fake image detection. A comparative analysis of 6 popular traditional machine learning models and 6 different CNN architectures to select the best possible model for further experimentation. The proposed model based on ResNet50 employed with powerful preprocessing techniques results in a perfect fake image detector having a total accuracy of 0.99 having an improvement of around 18% performance with other models.
format	Article
author	Hamid, Yasir Elyassami, Sanaa Gulzar, Yonis Balasaraswathi, Veeran Ranganathan Habuza, Tetiana Wani, Sharyar
author_facet	Hamid, Yasir Elyassami, Sanaa Gulzar, Yonis Balasaraswathi, Veeran Ranganathan Habuza, Tetiana Wani, Sharyar
author_sort	Hamid, Yasir
title	An improvised CNN model for fake image detection
title_short	An improvised CNN model for fake image detection
title_full	An improvised CNN model for fake image detection
title_fullStr	An improvised CNN model for fake image detection
title_full_unstemmed	An improvised CNN model for fake image detection
title_sort	improvised cnn model for fake image detection
publisher	Springer Nature
publishDate	2022
url	http://irep.iium.edu.my/101720/1/Screen%20Shot%202022-12-07%20at%208.23.03%20AM.png http://irep.iium.edu.my/101720/ https://link.springer.com/article/10.1007/s41870-022-01130-5
_version_	1751535954099699712
score	13.211869

An improvised CNN model for fake image detection

Similar Items