In this work, we deal with the problem of re compression based image forgery detection, where some regions of an image are modified illegitimately, hence giving rise to presence of dual compression characteristics within a single image. There have been some significant researches in this direction, in the last decade. However, almost all existing techniques fail to detect this form of forgery, when the first compression factor is greater than the second. We address this problem in re compression based forgery detection, here Recently, Machine Learning techniques have started gaining a lot of importance in the domain of digital image forensics. In this work, we propose a Convolution Neural Network based deep learning architecture, which is capable of detecting the presence of re compression based forgery in JPEG images. The proposed architecture works equally efficiently, even in cases where the first compression ratio is greater than the second. In this work, we also aim to localize the regions of image manipulation based on re compression features, using the trained neural network. Our experimental results prove that the proposed method outperforms the state of the art, with respect to forgery detection and localization accuracy.

翻译：本文研究基于重压缩的图像伪造检测问题，即图像中某些区域被非法篡改，导致单幅图像内出现双重压缩特征。过去十年间，该领域已取得若干重要研究成果。然而，当首次压缩因子大于二次压缩因子时，现有技术几乎都无法有效检测此类伪造。我们针对重压缩伪造检测中的这一难题展开研究。近年来，机器学习技术在数字图像取证领域日益受到重视。本文提出一种基于卷积神经网络的深度学习架构，能够有效检测JPEG图像中基于重压缩的伪造痕迹。即使首次压缩比大于二次压缩比的情况，该架构仍能保持同等检测效能。此外，本研究还利用训练完成的神经网络，基于重压缩特征实现篡改区域的精确定位。实验结果表明，所提方法在伪造检测与定位精度方面均优于当前最优技术。