Image Forgery Detection Using Deep Learning by Recompressing Images
Capturing images has been increasingly popular in recent years, owing to the widespread availability of cameras. Images are essential in our daily lives because they contain a wealth of information, and it is often required to enhance images to obtain additional information. A variety of tools are a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/3/403 |
| _version_ | 1797488316286763008 |
|---|---|
| author | Syed Sadaf Ali Iyyakutti Iyappan Ganapathi Ngoc-Son Vu Syed Danish Ali Neetesh Saxena Naoufel Werghi |
| author_facet | Syed Sadaf Ali Iyyakutti Iyappan Ganapathi Ngoc-Son Vu Syed Danish Ali Neetesh Saxena Naoufel Werghi |
| author_sort | Syed Sadaf Ali |
| collection | DOAJ |
| description | Capturing images has been increasingly popular in recent years, owing to the widespread availability of cameras. Images are essential in our daily lives because they contain a wealth of information, and it is often required to enhance images to obtain additional information. A variety of tools are available to improve image quality; nevertheless, they are also frequently used to falsify images, resulting in the spread of misinformation. This increases the severity and frequency of image forgeries, which is now a major source of concern. Numerous traditional techniques have been developed over time to detect image forgeries. In recent years, convolutional neural networks (CNNs) have received much attention, and CNN has also influenced the field of image forgery detection. However, most image forgery techniques based on CNN that exist in the literature are limited to detecting a specific type of forgery (either image splicing or copy-move). As a result, a technique capable of efficiently and accurately detecting the presence of unseen forgeries in an image is required. In this paper, we introduce a robust deep learning based system for identifying image forgeries in the context of double image compression. The difference between an image’s original and recompressed versions is used to train our model. The proposed model is lightweight, and its performance demonstrates that it is faster than state-of-the-art approaches. The experiment results are encouraging, with an overall validation accuracy of 92.23%. |
| first_indexed | 2024-03-10T00:01:20Z |
| format | Article |
| id | doaj.art-6a2b3d9b2eb64fe19cf6272055317804 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T00:01:20Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6a2b3d9b2eb64fe19cf62720553178042023-11-23T16:16:22ZengMDPI AGElectronics2079-92922022-01-0111340310.3390/electronics11030403Image Forgery Detection Using Deep Learning by Recompressing ImagesSyed Sadaf Ali0Iyyakutti Iyappan Ganapathi1Ngoc-Son Vu2Syed Danish Ali3Neetesh Saxena4Naoufel Werghi5ETIS, CY Cergy Paris Université, ENSEA, CNRS, UMR 8051, 95000 Cergy, FranceC2PS & KUCARS, Khalifa University, Abu Dhabi 127788, United Arab EmiratesETIS, CY Cergy Paris Université, ENSEA, CNRS, UMR 8051, 95000 Cergy, FranceMachine Intelligence Research (MIR) Labs Gwalior, Gwalior 474001, IndiaSchool of Computer Science and Informatics, Cardiff University, Cardiff CF10 3AT, UKC2PS & KUCARS, Khalifa University, Abu Dhabi 127788, United Arab EmiratesCapturing images has been increasingly popular in recent years, owing to the widespread availability of cameras. Images are essential in our daily lives because they contain a wealth of information, and it is often required to enhance images to obtain additional information. A variety of tools are available to improve image quality; nevertheless, they are also frequently used to falsify images, resulting in the spread of misinformation. This increases the severity and frequency of image forgeries, which is now a major source of concern. Numerous traditional techniques have been developed over time to detect image forgeries. In recent years, convolutional neural networks (CNNs) have received much attention, and CNN has also influenced the field of image forgery detection. However, most image forgery techniques based on CNN that exist in the literature are limited to detecting a specific type of forgery (either image splicing or copy-move). As a result, a technique capable of efficiently and accurately detecting the presence of unseen forgeries in an image is required. In this paper, we introduce a robust deep learning based system for identifying image forgeries in the context of double image compression. The difference between an image’s original and recompressed versions is used to train our model. The proposed model is lightweight, and its performance demonstrates that it is faster than state-of-the-art approaches. The experiment results are encouraging, with an overall validation accuracy of 92.23%.https://www.mdpi.com/2079-9292/11/3/403convolutional neural networksneural networksforgery detectionimage compressionimage processing |
| spellingShingle | Syed Sadaf Ali Iyyakutti Iyappan Ganapathi Ngoc-Son Vu Syed Danish Ali Neetesh Saxena Naoufel Werghi Image Forgery Detection Using Deep Learning by Recompressing Images Electronics convolutional neural networks neural networks forgery detection image compression image processing |
| title | Image Forgery Detection Using Deep Learning by Recompressing Images |
| title_full | Image Forgery Detection Using Deep Learning by Recompressing Images |
| title_fullStr | Image Forgery Detection Using Deep Learning by Recompressing Images |
| title_full_unstemmed | Image Forgery Detection Using Deep Learning by Recompressing Images |
| title_short | Image Forgery Detection Using Deep Learning by Recompressing Images |
| title_sort | image forgery detection using deep learning by recompressing images |
| topic | convolutional neural networks neural networks forgery detection image compression image processing |
| url | https://www.mdpi.com/2079-9292/11/3/403 |
| work_keys_str_mv | AT syedsadafali imageforgerydetectionusingdeeplearningbyrecompressingimages AT iyyakuttiiyappanganapathi imageforgerydetectionusingdeeplearningbyrecompressingimages AT ngocsonvu imageforgerydetectionusingdeeplearningbyrecompressingimages AT syeddanishali imageforgerydetectionusingdeeplearningbyrecompressingimages AT neeteshsaxena imageforgerydetectionusingdeeplearningbyrecompressingimages AT naoufelwerghi imageforgerydetectionusingdeeplearningbyrecompressingimages |