Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics

Abstract

As JPEG is the most widely used image format, the importance of tampering detection for JPEG images in blind forensics is self-evident. In this area, extracting effective statistical characteristics from a JPEG image for classification remains a challenge. Effective features are designed manually in traditional methods, suggesting that extensive labor-consuming research and derivation is required. In this paper, we propose a novel image tampering detection method based on deep multi-scale discriminative networks (MSD-Nets). The multi-scale module is designed to automatically extract multiple features from the discrete cosine transform (DCT) coefficient histograms of the JPEG image. This module can capture the characteristic information in different scale spaces. In addition, a discriminative module is also utilized to improve the detection effect of the networks in those difficult situations when the first compression quality (QF 1) is higher than the second one (QF 2). A special network in this module is designed to distinguish the small statistical difference between authentic and tampered regions in these cases. Finally, a probability map can be obtained and the specific tampering area is located using the last classification results. Extensive experiments demonstrate the superiority of our proposed method in both quantitative and qualitative metrics when compared with state-of-the-art approaches. . 2018. Deep multi-scale discriminative networks for double JPEG compression forensics.

Image Splicing Detection, Localization and Attribution via JPEG Primary Quantization Matrix Estimation and Clustering

“…More recently, a new class of CNN-based methods have been proposed. They are able to improve the spatial resolution of DJPEG localization and then can be conveniently used for tampering localization, (see, for instance, [19], [20] -for both aligned and not-aligned DJPEG detection, and [4] -for the aligned DJPEG case). All the above methods focus on the SJPEG vs DJPEG scenario, that is, they work under the assumption that the tampered areas are double compressed while the background is single compressed.…”

“…If any of the sums in brackets at the denominator is zero, the denominator is arbitrarily set to one. MCC is particularly helpfull in the case of unbalanced classed, like it is almost always the case for tampering localization 4 . The identification of spliced regions coming from different donor images is a new goal addressed in this paper, so no established metric exists to measure the performance with respect to this task.…”

“…2) the spliced region (or regions) is taken from a non compressed image and spliced into a JPEG image. After recompression, the forged area has undergone only a single JPEG compression (SJPEG) while the background has been compressed twice [3], [4], [5]. In the following, we refer to this situation as DJPEG vs SJPEG detection.…”

Exposing Digital Image Forgeries by Detecting Contextual Abnormality Using Convolutional Neural Networks

“…Approaches based on deep neural networks have also been used to investigate low-level image features. Methods that focus on low-level features mostly focus on detecting local inconsistencies or statistical features relating to the manipulated images [12][13][14][15][16].…”

DR-GAN: Distribution Regularization for Text-to-Image Generation

“…Generating photographic images from text descriptions (known as Text-to-Image Generation, T2I) is a challenging cross-modal generation technique that is a core component in many computer vision tasks such as Image Editing [28], [51], Story Visualization [53], and Multimedia Retrieval [19]. Compared with the image generation [26], [17], [22] and image processing [6], [5], [23] tasks between the same mode, it is difficult to build the heterogeneous semantic bridge between text and image [54], [48], [40]. Many state-of-the-art T2I algorithms [31], [25], [36], [9], [3], [42] first extract text features, then use Generative Adversarial Networks (GANs) [7] to generate the corresponding image.…”