A novel contrast enhancement forensics based on convolutional neural networks

• Published in: Signal processing. Image communication 2018-04, Vol.63, p.149-160
• Main Authors: Sun, Jee-Young, Kim, Seung-Wook, Lee, Sang-Won, Ko, Sung-Jea
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer simulation; Contrast enhancement; Convolutional neural networks; Deep learning; Digital image forensics; Digital imaging; Feature extraction; Forensic computing; Gray level co-occurrence matrix; Image contrast; Image enhancement; Image processing systems; Neural networks; Retouching; Signal processing; Signal to noise ratio; Statistical methods
• ISSN: 0923-5965; 1879-2677
• DOI: 10.1016/j.image.2018.02.001

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. •A novel CNN-based contrast enhancement (CE) forensic method is proposed.•Gray level co-occurrence matrix (GLCM) is fed into the CNN.•The CNN trained with GLCM is superior to the one trained using the image input.•The proposed method is robust to state-of-the-art anti-forensic attacks.•The proposed method outperforms the conventional CE forensic approaches.