General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network
Within digital forensics, a notable emphasis is placed on the detection of the application of fundamental image-editing operators, including but not limited to median filters, average filters, contrast enhancement, resampling, and various other operations closely associated with these techniques. Wh...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/21/4537 |
| _version_ | 1797631584497565696 |
|---|---|
| author | Sajjad Ahmed Byungun Yoon Sparsh Sharma Saurabh Singh Saiful Islam |
| author_facet | Sajjad Ahmed Byungun Yoon Sparsh Sharma Saurabh Singh Saiful Islam |
| author_sort | Sajjad Ahmed |
| collection | DOAJ |
| description | Within digital forensics, a notable emphasis is placed on the detection of the application of fundamental image-editing operators, including but not limited to median filters, average filters, contrast enhancement, resampling, and various other operations closely associated with these techniques. When conducting a historical analysis of an image that has potentially undergone various modifications in the past, it is a logical initial approach to search for alterations made by fundamental operators. This paper presents the development of a deep-learning-based system designed for the purpose of detecting fundamental manipulation operations. The research involved training a multilayer perceptron using a feature set of 36 dimensions derived from the gray-level co-occurrence matrix, gray-level run-length matrix, and normalized streak area. The system detected median filtering, mean filtering, the introduction of additive white Gaussian noise, and the application of JPEG compression in digital Images. Our system, which utilizes a multilayer perceptron trained with a 36-feature set, achieved an accuracy of 99.46% and outperformed state-of-the-art deep-learning-based solutions, which achieved an accuracy of 97.89%. |
| first_indexed | 2024-03-11T11:25:33Z |
| format | Article |
| id | doaj.art-a3065e3081f2427db799d7f0954dd521 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T11:25:33Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-a3065e3081f2427db799d7f0954dd5212023-11-10T15:08:12ZengMDPI AGMathematics2227-73902023-11-011121453710.3390/math11214537General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural NetworkSajjad Ahmed0Byungun Yoon1Sparsh Sharma2Saurabh Singh3Saiful Islam4School of Computer Science Engineering, VIT Bhopal University, Bhopal-Indore Highway, Kothrikalan, Sehore 466114, Madhya Pradesh, IndiaDepartment of Industrial & System Engineering, Dongguk University, Seoul 04620, Republic of KoreaDepartment of Computer Science Engineering, National Institute of Technology Srinagar, Srinagar 190001, Jammu and Kashmir, IndiaDepartment of AI and Big Data, Woosong University, Seoul 34606, Republic of KoreaZakir Husain College of Engineering and Technology, Aligarh Muslim University, Aligarh 202002, Uttar Pradesh, IndiaWithin digital forensics, a notable emphasis is placed on the detection of the application of fundamental image-editing operators, including but not limited to median filters, average filters, contrast enhancement, resampling, and various other operations closely associated with these techniques. When conducting a historical analysis of an image that has potentially undergone various modifications in the past, it is a logical initial approach to search for alterations made by fundamental operators. This paper presents the development of a deep-learning-based system designed for the purpose of detecting fundamental manipulation operations. The research involved training a multilayer perceptron using a feature set of 36 dimensions derived from the gray-level co-occurrence matrix, gray-level run-length matrix, and normalized streak area. The system detected median filtering, mean filtering, the introduction of additive white Gaussian noise, and the application of JPEG compression in digital Images. Our system, which utilizes a multilayer perceptron trained with a 36-feature set, achieved an accuracy of 99.46% and outperformed state-of-the-art deep-learning-based solutions, which achieved an accuracy of 97.89%.https://www.mdpi.com/2227-7390/11/21/4537digital image forensicsmultilayer perceptrongeneral-purpose image manipulation detectionoperator detectionneural networktexture features |
| spellingShingle | Sajjad Ahmed Byungun Yoon Sparsh Sharma Saurabh Singh Saiful Islam General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network Mathematics digital image forensics multilayer perceptron general-purpose image manipulation detection operator detection neural network texture features |
| title | General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network |
| title_full | General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network |
| title_fullStr | General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network |
| title_full_unstemmed | General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network |
| title_short | General Image Manipulation Detection Using Feature Engineering and a Deep Feed-Forward Neural Network |
| title_sort | general image manipulation detection using feature engineering and a deep feed forward neural network |
| topic | digital image forensics multilayer perceptron general-purpose image manipulation detection operator detection neural network texture features |
| url | https://www.mdpi.com/2227-7390/11/21/4537 |
| work_keys_str_mv | AT sajjadahmed generalimagemanipulationdetectionusingfeatureengineeringandadeepfeedforwardneuralnetwork AT byungunyoon generalimagemanipulationdetectionusingfeatureengineeringandadeepfeedforwardneuralnetwork AT sparshsharma generalimagemanipulationdetectionusingfeatureengineeringandadeepfeedforwardneuralnetwork AT saurabhsingh generalimagemanipulationdetectionusingfeatureengineeringandadeepfeedforwardneuralnetwork AT saifulislam generalimagemanipulationdetectionusingfeatureengineeringandadeepfeedforwardneuralnetwork |