• Corpus ID: 214605610

Block-level double JPEG compression detection for image forgery localization

  title={Block-level double JPEG compression detection for image forgery localization},
  author={Vinay Verma and Deepak Singh and Nitin Khanna},
  journal={arXiv: Image and Video Processing},
Forged images have a ubiquitous presence in today's world due to ease of availability of image manipulation tools. In this letter, we propose a deep learning-based novel approach which utilizes the inherent relationship between DCT coefficient histograms and corresponding quantization step sizes to distinguish between original and forged regions in a JPEG image, based on the detection of single and double compressed blocks, without fully decompressing the JPEG image. We consider a diverse set… 

Figures and Tables from this paper

Double JPEG Compression Detection for Distinguishable Blocks in Images Compressed with Same Quantization Matrix

A novel deep learning based approach that utilizes spatial and frequency domain information from the error blocks obtained from multiple compression stages and uses a multi-column CNN architecture to classify distinguishable blocks of size 8×8.

Q-matrix Unaware Double JPEG Detection using DCT-Domain Deep BiLSTM Network

This paper directly extracts the quantized DCT coefficients from the JPEG images without decompressing them in the pixel domain, obtains all AC frequencies’ histograms, uses a module based on 1×1 depth-wise convolutions to learn the inherent relation between each histogram and corresponding qfactor, and utilizes a tailor-made BiLSTM network for selectively encoding these feature vector sequences.

AI-Based Compression: A New Unintended Counter Attack on JPEG-Related Image Forensic Detectors?

This paper is the first to consider AI-based compression with digital image analysis tools and chooses the best detector to date, an AI- based compression method and the Casia v2 database that contains both splicing and copy-move (all publicly available).

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

A convolutional neural network that uses discrete cosine transform (DCT) coefficients, where compression artifacts remain, to localize image manipulation and outperforms traditional and deep neural network-based methods in detecting and localizing tampered regions.

Adaptive content suppression based on shared‐hidden‐layer convolutional autoencoder for blind image forensics

This article investigates DJPEG compression detection in aligned and nonaligned tampering cases using adaptive image content removal based on a shared‐hidden‐layer convolutional autoencoder for preprocessing and indicates appropriate performance in the aligned and especially nonaligned cases.

CAT-Net: Compression Artifact Tracing Network for Detection and Localization of Image Splicing

CAT-Net is proposed, an end-to-end fully convolutional neural network including RGB and DCT streams, to learn forensic features of compression artifacts on RGB andDCT domains jointly to localize spliced regions in JPEG or non-JPEG images.

GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection

A novel Gated Context Attention Network (GCA-Net) that utilizes non-local attention in conjunction with a gating mechanism in order to capture the finer image discrepancies and better identify forged regions is proposed.

A comprehensive survey of image and video forgery techniques: variants, challenges, and future directions

A detailed, comprehensive and systematic survey of current trends in the field of image and video forensics, the applications of image/video forensics and the existing datasets is provided, pointing out the challenges and the future directions for researchers.



A novel forensic image analysis tool for discovering double JPEG compression clues

A novel technique to discover double JPEG compression traces, which discriminates single compressed images from double counterparts, estimates the first quantization in double compression, and localizes tampered regions in a forgery examination is presented.

Discriminating multiple JPEG compressions using first digit features

A forensic method is proposed based on the analysis of the distribution of the first significant digits of the discrete cosine transform coefficients, which follow Benford's law in images compressed just once, which extends and outperforms the previously-published algorithms for double JPEG compression detection.

Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis

Improved DCT coefficient analysis for forgery localization in JPEG images

A statistical test to discriminate between original and forged regions in JPEG images, under the hypothesis that the former are doubly compressed while the latter are singly compressed, demonstrates a better discriminating behavior with respect to previously proposed methods.

Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks

Estimation of Primary Quantization Matrix in Double Compressed JPEG Images

It is explained in this paper, how double compression detection techniques and primary quantization matrix estimators can be used in steganalysis of JPEG files and in digital forensic analysis for detection of digital forgeries.

A Novel Method for Detecting Cropped and Recompressed Image Block

A novel method for the detection of image tampering operations in JPEG images by exploiting the blocking artifact characteristics matrix (BACM) to train a support vector machine (SVM) classifier for recognizing whether an image is an original JPEG image or it has been cropped from another JPEG image and re-saved as a JPEG image.

Localization of JPEG Double Compression Through Multi-domain Convolutional Neural Networks

This paper proposes a step forward in this direction by analyzing how a single or double JPEG compression can be revealed and localized using convolutional neural networks (CNNs).

Detection of double JPEG compression using modified DenseNet model

A modified version of DenseNet (densely connected convolutional networks) is proposed to accomplish the detection task of primary JPEG compression among double compressed images, with great improvement compared to the-state-of-the-art method especially on the classification accuracy among images with lower quality factors.