A framework of generative adversarial networks with novel loss for JPEG restoration and anti-forensics
- 12 April 2021
- journal article
- research article
- Published by Springer Nature in Multimedia Systems
- Vol. 27 (6) , 1075-1089
Abstract
No abstract availableKeywords
Funding Information
- China Postdoctoral Science Foundation (2020M683051)
- Fundamental Research Funds for the Central Universities, Sun Yat-sen University (67000-31610131)
This publication has 26 references indexed in Scilit:
- Identification of Various Image Operations Using Residual-Based FeaturesIEEE Transactions on Circuits and Systems for Video Technology, 2016
- JPEG Anti-Forensics With Improved Tradeoff Between Forensic Undetectability and Image QualityIEEE Transactions on Information Forensics and Security, 2014
- Compression Artifact Reduction by Overlapped-Block Transform Coefficient Estimation With Block SimilarityIEEE Transactions on Image Processing, 2013
- Rich Models for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- ”Break Our Steganographic System”: The Ins and Outs of Organizing BOSS2011
- Countering Counter-Forensics: The Case of JPEG Compression2011
- Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color ImagesIEEE Transactions on Image Processing, 2007
- Identification of bitmap compression history: jpeg detection and quantizer estimationIEEE Transactions on Image Processing, 2003
- A mathematical analysis of the DCT coefficient distributions for imagesIEEE Transactions on Image Processing, 2000