Abstract
Contrast enhancement (CE), one of the most popular digital image retouching technologies, is frequently utilized for malicious purposes. As a consequence, verifying the authenticity of digital images in CE forensics has recently drawn significant attention. Current CE forensic methods can be performed using relatively simple handcrafted features based on first-and second-order statistics, but these methods have encountered difficulties in detecting modern counter-forensic attacks. In this paper, we present a novel CE forensic method based on convolutional neural network (CNN). To the best of our knowledge, this is the first work that applies CNN to CE forensics. Unlike the conventional CNN in other research fields that generally accepts the original image as its input, in the proposed method, we feed the CNN with the gray-level co-occurrence matrix (GLCM) which contains traceable features for CE forensics, and is always of the same size, even for input images of different resolutions. By learning the hierarchical feature representations and optimizing the classification results, the proposed CNN can extract a variety of appropriate features to detect the manipulation. The performance of the proposed method is compared to that of three conventional forensic methods. The comparative evaluation is conducted within a dataset consisting of unaltered images, contrast-enhanced images, and counter-forensically attacked images. The experimental results indicate that the proposed method outperforms conventional forensic methods in terms of forgery-detection accuracy, especially in dealing with counter-forensic attacks.
| Original language | English |
|---|---|
| Journal | Signal Processing: Image Communication |
| DOIs | |
| Publication status | Accepted/In press - 2018 Jan 1 |
Fingerprint
Keywords
- Contrast enhancement
- Convolutional neural networks
- Deep learning
- Digital image forensics
- Gray level co-occurrence matrix
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
Cite this
A novel contrast enhancement forensics based on convolutional neural networks. / Sun, Jee Young; Kim, Seung Wook; Lee, Sang Won; Ko, Sung-Jea.
In: Signal Processing: Image Communication, 01.01.2018.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A novel contrast enhancement forensics based on convolutional neural networks
AU - Sun, Jee Young
AU - Kim, Seung Wook
AU - Lee, Sang Won
AU - Ko, Sung-Jea
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Contrast enhancement (CE), one of the most popular digital image retouching technologies, is frequently utilized for malicious purposes. As a consequence, verifying the authenticity of digital images in CE forensics has recently drawn significant attention. Current CE forensic methods can be performed using relatively simple handcrafted features based on first-and second-order statistics, but these methods have encountered difficulties in detecting modern counter-forensic attacks. In this paper, we present a novel CE forensic method based on convolutional neural network (CNN). To the best of our knowledge, this is the first work that applies CNN to CE forensics. Unlike the conventional CNN in other research fields that generally accepts the original image as its input, in the proposed method, we feed the CNN with the gray-level co-occurrence matrix (GLCM) which contains traceable features for CE forensics, and is always of the same size, even for input images of different resolutions. By learning the hierarchical feature representations and optimizing the classification results, the proposed CNN can extract a variety of appropriate features to detect the manipulation. The performance of the proposed method is compared to that of three conventional forensic methods. The comparative evaluation is conducted within a dataset consisting of unaltered images, contrast-enhanced images, and counter-forensically attacked images. The experimental results indicate that the proposed method outperforms conventional forensic methods in terms of forgery-detection accuracy, especially in dealing with counter-forensic attacks.
AB - Contrast enhancement (CE), one of the most popular digital image retouching technologies, is frequently utilized for malicious purposes. As a consequence, verifying the authenticity of digital images in CE forensics has recently drawn significant attention. Current CE forensic methods can be performed using relatively simple handcrafted features based on first-and second-order statistics, but these methods have encountered difficulties in detecting modern counter-forensic attacks. In this paper, we present a novel CE forensic method based on convolutional neural network (CNN). To the best of our knowledge, this is the first work that applies CNN to CE forensics. Unlike the conventional CNN in other research fields that generally accepts the original image as its input, in the proposed method, we feed the CNN with the gray-level co-occurrence matrix (GLCM) which contains traceable features for CE forensics, and is always of the same size, even for input images of different resolutions. By learning the hierarchical feature representations and optimizing the classification results, the proposed CNN can extract a variety of appropriate features to detect the manipulation. The performance of the proposed method is compared to that of three conventional forensic methods. The comparative evaluation is conducted within a dataset consisting of unaltered images, contrast-enhanced images, and counter-forensically attacked images. The experimental results indicate that the proposed method outperforms conventional forensic methods in terms of forgery-detection accuracy, especially in dealing with counter-forensic attacks.
KW - Contrast enhancement
KW - Convolutional neural networks
KW - Deep learning
KW - Digital image forensics
KW - Gray level co-occurrence matrix
UR - http://www.scopus.com/inward/record.url?scp=85042145269&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85042145269&partnerID=8YFLogxK
U2 - 10.1016/j.image.2018.02.001
DO - 10.1016/j.image.2018.02.001
M3 - Article
AN - SCOPUS:85042145269
JO - Signal Processing: Image Communication
JF - Signal Processing: Image Communication
SN - 0923-5965
ER -