An Evaluation of Convolutional Neural Network (CNN) Model for Copy-Move and Splicing Forgery Detection
Image forgeries such as copy-move and splicing are very common due to the availability of the advancement in software editing techniques. However, most of the existing methods for forgery detection consider only one type of image forgery due to the reason that both forgeries have different traits....
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IJISAE
2023
|
Subjects: | |
Online Access: | http://eprints.uthm.edu.my/11523/1/J16045_03bd2e85e9c5ccb6bf013a56ac2dba37.pdf http://eprints.uthm.edu.my/11523/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uthm.eprints.11523 |
---|---|
record_format |
eprints |
spelling |
my.uthm.eprints.115232024-08-12T01:49:42Z http://eprints.uthm.edu.my/11523/ An Evaluation of Convolutional Neural Network (CNN) Model for Copy-Move and Splicing Forgery Detection Thiiban Muniappan, Thiiban Muniappan Abd Warif, Nor Bakiah Ismail, Ahsiah Mat Abir, Noor Atikah T Technology (General) Image forgeries such as copy-move and splicing are very common due to the availability of the advancement in software editing techniques. However, most of the existing methods for forgery detection consider only one type of image forgery due to the reason that both forgeries have different traits. In this paper, a Convolutional Neural Network (CNN) model which is one of the deep learning approaches is simulated and analyzed to detect any forged image without knowing their types of forgeries. In the model, three phases are involved: Data Preprocessing, Feature Extraction, and Classification. The model learns to extract features from convolutional, pooling, and Rectified Linear unit layer, and classified the image whether it is original or forged using fully connected layer. For the experimental works, three datasets namely MICC-F2000 (2000 images), CASIA 1 (1721 images), and CASIA 2 (12615 images) are tested and compared with existing deep learning-based methods. The results show that the CNN model achieved the highest performance with accuracy of 79% for CASIA 1 and 89% for CASIA 2. IJISAE 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/11523/1/J16045_03bd2e85e9c5ccb6bf013a56ac2dba37.pdf Thiiban Muniappan, Thiiban Muniappan and Abd Warif, Nor Bakiah and Ismail, Ahsiah and Mat Abir, Noor Atikah (2023) An Evaluation of Convolutional Neural Network (CNN) Model for Copy-Move and Splicing Forgery Detection. International Journal of INTELLIGENT SYSTEMS AND APPLICATIONS IN ENGINEERING. pp. 730-740. ISSN 2147-6799 |
institution |
Universiti Tun Hussein Onn Malaysia |
building |
UTHM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tun Hussein Onn Malaysia |
content_source |
UTHM Institutional Repository |
url_provider |
http://eprints.uthm.edu.my/ |
language |
English |
topic |
T Technology (General) |
spellingShingle |
T Technology (General) Thiiban Muniappan, Thiiban Muniappan Abd Warif, Nor Bakiah Ismail, Ahsiah Mat Abir, Noor Atikah An Evaluation of Convolutional Neural Network (CNN) Model for Copy-Move and Splicing Forgery Detection |
description |
Image forgeries such as copy-move and splicing are very common due to the availability of the advancement in
software editing techniques. However, most of the existing methods for forgery detection consider only one type of image forgery due to the reason that both forgeries have different traits. In this paper, a Convolutional Neural Network (CNN) model which is one of the deep learning approaches is simulated and analyzed to detect any forged image without knowing their types of forgeries. In the model, three phases are involved: Data Preprocessing, Feature Extraction, and Classification. The model learns to extract features from convolutional, pooling, and Rectified Linear unit layer, and classified the image whether it is original or forged using fully connected layer. For the experimental works, three datasets namely MICC-F2000 (2000 images), CASIA 1 (1721 images), and CASIA 2 (12615 images) are tested and compared with existing deep learning-based methods. The results show that the CNN model achieved the highest performance with accuracy of 79% for CASIA 1 and 89% for CASIA 2. |
format |
Article |
author |
Thiiban Muniappan, Thiiban Muniappan Abd Warif, Nor Bakiah Ismail, Ahsiah Mat Abir, Noor Atikah |
author_facet |
Thiiban Muniappan, Thiiban Muniappan Abd Warif, Nor Bakiah Ismail, Ahsiah Mat Abir, Noor Atikah |
author_sort |
Thiiban Muniappan, Thiiban Muniappan |
title |
An Evaluation of Convolutional Neural Network (CNN) Model
for Copy-Move and Splicing Forgery Detection |
title_short |
An Evaluation of Convolutional Neural Network (CNN) Model
for Copy-Move and Splicing Forgery Detection |
title_full |
An Evaluation of Convolutional Neural Network (CNN) Model
for Copy-Move and Splicing Forgery Detection |
title_fullStr |
An Evaluation of Convolutional Neural Network (CNN) Model
for Copy-Move and Splicing Forgery Detection |
title_full_unstemmed |
An Evaluation of Convolutional Neural Network (CNN) Model
for Copy-Move and Splicing Forgery Detection |
title_sort |
evaluation of convolutional neural network (cnn) model
for copy-move and splicing forgery detection |
publisher |
IJISAE |
publishDate |
2023 |
url |
http://eprints.uthm.edu.my/11523/1/J16045_03bd2e85e9c5ccb6bf013a56ac2dba37.pdf http://eprints.uthm.edu.my/11523/ |
_version_ |
1809145063461093376 |
score |
13.19449 |