DCT-domain deep convolutional neural networks for multiple JPEG compression classification

Abstract

With the rapid advancements in digital imaging systems and networking, low-cost hand-held image capture devices equipped with network connectivity are becoming ubiquitous. This ease of digital image capture and sharing is also accompanied by widespread usage of user-friendly image editing software. Thus, we are in an era where digital images can be very easily used for the massive spread of false information and their integrity need to be seriously questioned. Application of multiple lossy compressions on images is an essential part of any image editing pipeline involving lossy compressed images. This paper aims to address the problem of classifying images based on the number of JPEG compressions they have undergone, by utilizing deep convolutional neural networks in DCT domain. The proposed system incorporates a well designed pre-processing step before feeding the image data to CNN to capture essential characteristics of compression artifacts and make the system image content independent. Detailed experiments are performed to optimize different aspects of the system, such as depth of CNN, number of DCT frequencies, and execution time. Results on the standard UCID dataset demonstrate that the proposed system outperforms existing systems for multiple JPEG compression detection and is capable of classifying more number of re-compression cycles then existing systems.

Multi-Patch Aggregation Models for Resampling Detection

“…Since the accuracy is contingent on the sharpness of peak, it is obsevred the performance of the method quickly degrades for patches less than 512 × 512. [3] 1024 × 1024 512 × 512 MISLnet [7] 256 × 256 256 × 256 Li et al [14] 512 × 512 512 × 512 Verma et al [9] 512 × 384 128 × 128 Kirchner et al [15] 1024 × 1024 512 × 512 Bianchi et al [2] 1024 × 1024 512 × 512 Quan et al [10] <1024 × 1024 233 × 233 kernel size proportional to tensor's height and width to reduce all tensors to the same size. However, in our experiments this resulted in poor performance, see results for the Max-Pooling Network (MPN) in Table 3.…”

“…On the other hand one can always choose a large patch size for better performance. But the downside of this choice is that it won't work for smaller image sizes and the algorithm would incur excessive computations and processing time and poor manipulation localization [8,9]. It is perhaps for this reason that many recent works have considered images of roughly the same size and consequently a fixed patch size.…”

Convolutional Neural Network for Copy-Move Forgery Detection

“…The DCT domain feeds the input of the CNN by transferring the row of quantized DCT coefficients from the JPEG file to data classification. The processing of the data in the classification stage will generate a histogram for each patch and concatenate all of the histograms to feed the CNN [13].…”

Exploring Semantic Segmentation on the DCT Representation

“…One example is multiple JPEG compression detection. Verma et al [23] computed histograms of different DCT sub-bands, then concatenated these histograms to form a 1-D vector. This vector would be sent to a 1-D CNN to do detection.…”