Detection and localization enhancement for satellite images with small forgeries using modified GAN-based CNN structure
The image forgery process can be simply defined as inserting some objects of different sizes to vanish some structures or scenes. Satellite images can be forged in many ways, such as copy-paste, copy-move, and splicing processes. Recent approaches present a generative adversarial network (GAN) as an...
Saved in:
Main Authors: | , , |
---|---|
Format: | EJournal Article |
Published: |
Universitas Ahmad Dahlan,
2020-11-30.
|
Subjects: | |
Online Access: | Get Fulltext |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 02944 am a22002893u 4500 | ||
---|---|---|---|
001 | IJAIN_548_ijain_v6i3_p278-289 | ||
042 | |a dc | ||
100 | 1 | 0 | |a Fouad, Mohamed Mahmoud |e author |
100 | 1 | 0 | |e contributor |
700 | 1 | 0 | |a Mostafa, Eslam Magdy |e author |
700 | 1 | 0 | |a Elshafey, Mohamed Abdelmoneim |e author |
245 | 0 | 0 | |a Detection and localization enhancement for satellite images with small forgeries using modified GAN-based CNN structure |
260 | |b Universitas Ahmad Dahlan, |c 2020-11-30. | ||
500 | |a https://ijain.org/index.php/IJAIN/article/view/548 | ||
520 | |a The image forgery process can be simply defined as inserting some objects of different sizes to vanish some structures or scenes. Satellite images can be forged in many ways, such as copy-paste, copy-move, and splicing processes. Recent approaches present a generative adversarial network (GAN) as an effective method for identifying the presence of spliced forgeries and identifying their locations with a higher detection accuracy of large- and medium-sized forgeries. However, such recent approaches clearly show limited detection accuracy of small-sized forgeries. Accordingly, the localization step of such small-sized forgeries is negatively impacted. In this paper, two different approaches for detecting and localizing small-sized forgeries in satellite images are proposed. The first approach is inspired by a recently presented GAN-based approach and is modified to an enhanced version. The experimental results manifest that the detection accuracy of the first proposed approach noticeably increased to 86% compared to its inspiring one with 79% for the small-sized forgeries. Whereas, the second proposed approach uses a different design of a CNN-based discriminator to significantly enhance the detection accuracy to 94%, using the same dataset obtained from NASA and the US Geological Survey (USGS) for validation and testing. Furthermore, the results show a comparable detection accuracy in large- and medium-sized forgeries using the two proposed approaches compared to the competing ones. This study can be applied in the forensic field, with clear discrimination between the forged and pristine images. | ||
540 | |a Copyright (c) 2020 Mohamed Mahmoud Fouad, Eslam Magdy Mostafa, Mohamed Abdelmoneim Elshafey | ||
540 | |a https://creativecommons.org/licenses/by-sa/4.0 | ||
546 | |a eng | ||
690 | |a CNN; GAN; Satellite Image Forgery; Transfer Learning; FReLU Activation Function | ||
655 | 7 | |a info:eu-repo/semantics/article |2 local | |
655 | 7 | |a info:eu-repo/semantics/publishedVersion |2 local | |
655 | 7 | |2 local | |
786 | 0 | |n International Journal of Advances in Intelligent Informatics; Vol 6, No 3 (2020): November 2020; 278-289 | |
786 | 0 | |n 2548-3161 | |
786 | 0 | |n 2442-6571 | |
787 | 0 | |n https://ijain.org/index.php/IJAIN/article/view/548/ijain_v6i3_p278-289 | |
856 | 4 | 1 | |u https://ijain.org/index.php/IJAIN/article/view/548/ijain_v6i3_p278-289 |z Get Fulltext |