A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection
Open Access
- 16 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 133488-133502
Abstract
Due to limited computational and memory resources, current deep learning models accept only rather small images in input, calling for preliminary image resizing. This is not a problem for high-level vision problems, where discriminative features are barely affected by resizing. On the contrary, in image forensics, resizing tends to destroy precious high-frequency details, impacting heavily on performance. One can avoid resizing by means of patch-wise processing, at the cost of renouncing whole-image analysis. In this work, we propose a CNN-based image forgery detection framework which makes decisions based on full-resolution information gathered from the whole image. Thanks to gradient checkpointing, the framework is trainable end-to-end with limited memory resources and weak (image-level) supervision, allowing for the joint optimization of all parameters. Experiments on widespread image forensics datasets prove the good performance of the proposed approach, which largely outperforms all baselines and all reference methods.Keywords
All Related Versions
Funding Information
- Google Faculty Research Award
- Air Force Research Laboratory
- Defense Advanced Research Projects Agency (FA8750-16-2-0204)
- PREMIER Project
- Italian Ministry of Education, University, and Research within the Progetti di Ricerca di Interesse Nazionale (PRIN) 2017 Program
This publication has 43 references indexed in Scilit:
- A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer2016
- Splicebuster: A new blind image splicing detector2015
- Efficient Dense-Field Copy–Move Forgery DetectionIEEE Transactions on Information Forensics and Security, 2015
- Image forgery detection through residual-based local descriptors and block-matching2014
- Passive Image-Splicing Detection by a 2-D Noncausal Markov ModelIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Digital image splicing detection based on Markov features in DCT and DWT domainPattern Recognition, 2012
- Rich Models for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2012
- Using noise inconsistencies for blind image forensicsImage and Vision Computing, 2009
- Steganalysis Versus Splicing DetectionLecture Notes in Computer Science, 2008
- UCID: an uncompressed color image database2003