arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12947eess.IVcs.CVcs.LGcs.MM
收藏

学习JPEG压缩伪影的图像篡改检测与定位

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院);NAVER WEBTOON AI(NAVER网络漫画AI);Samsung Electronics Co., Ltd.(三星电子株式会社)

Myung-Joon Kwon, Seung-Hun Nam, In-Jae Yu, Heung-Kyu Lee, Changick Kim

摘要:

检测和定位图像操纵是必要的,以打击恶意使用的图像编辑技术。因此,必须通过分析图像中的固有统计来区分真实区域和篡改区域。我们专注于JPEG压缩文物在图像采集和编辑。我们提出了一种卷积神经网络(CNN),它使用离散余弦变换(DCT)系数,其中压缩伪影仍然存在,以本地化图像操作。标准CNN无法学习DCT系数的分布,因为卷积会丢弃DCT系数所必需的空间坐标。我们说明了如何设计和训练一个神经网络,可以学习DCT系数的分布。此外,我们介绍了压缩伪影跟踪网络(CAT-Net),它联合使用图像采集伪影和压缩伪影。它在检测和定位篡改区域方面明显优于传统和基于深度神经网络的方法。

英文摘要:

Detecting and localizing image manipulation are necessary to counter malicious use of image editing techniques. Accordingly, it is essential to distinguish between authentic and tampered regions by analyzing intrinsic statistics in an image. We focus on JPEG compression artifacts left during image acquisition and editing. We propose a convolutional neural network (CNN) that uses discrete cosine transform (DCT) coefficients, where compression artifacts remain, to localize image manipulation. Standard CNNs cannot learn the distribution of DCT coefficients because the convolution throws away the spatial coordinates, which are essential for DCT coefficients. We illustrate how to design and train a neural network that can learn the distribution of DCT coefficients. Furthermore, we introduce Compression Artifact Tracing Network (CAT-Net) that jointly uses image acquisition artifacts and compression artifacts. It significantly outperforms traditional and deep neural network-based methods in detecting and localizing tampered regions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑