Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
arXiv:2108.12947 · doi:10.1007/s11263-022-01617-5
Abstract
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.
arXiv commentThe version of record of this article, published in the International Journal of Computer Vision (IJCV), is available online at Publisher's website: https://link.springer.com/article/10.1007/s11263-022-01617-5 ; Code is available at: https://github.com/mjkwon2021/CAT-Net
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Media Forensics and DeepFakes: an overview
- SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization
- Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks
- Deep Convolutional Neural Network for Identifying Seam-Carving Forgery