I reimplement a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet.
In this repository, we release many paper related things, including
USCISI-CMFD Dataset
This copy-move forgery detection(CMFD) dataset relies on
More precisely, we synthesize a copy-move forgery sample using the following steps
More detailed description can be found in paper.
This USCISI-CMFD dataset folder contains the following things:
NOTE due to the repository size limit, the full USCISI-CMFD dataset will be provided upon request.
pip install -r requirements.txt
python train.py
with custom argurments:
usage: Buster Net [-h] [-n NUM_WORKERS] [-b BATCH_SIZE] [--num_gpus NUM_GPUS]
[--freeze_layers [FREEZE_LAYERS [FREEZE_LAYERS ...]]]
[--lr LR] [--optim OPTIM] [--num_epochs NUM_EPOCHS]
[--val_interval VAL_INTERVAL]
[--save_interval SAVE_INTERVAL]
[--es_min_delta ES_MIN_DELTA] [--es_patience ES_PATIENCE]
[--lmdb_dir LMDB_DIR] [--log_path LOG_PATH]
[-w LOAD_WEIGHTS] [--saved_path SAVED_PATH]
If you use the provided code or data in any publication, please kindly cite the following paper.
@inproceedings{wu2018eccv,
title={BusterNet: Detecting Image Copy-Move Forgery With Source/Target Localization},
author={Wu, Yue, and AbdAlmageed, Wael and Natarajan, Prem},
booktitle={European Conference on Computer Vision (ECCV)},
year={2018},
organization={Springer},
}
The Software is made available for academic or non-commercial purposes only. The license is for a copy of the program for an unlimited term. Individuals requesting a license for commercial use must pay for a commercial license.
USC Stevens Institute for Innovation
University of Southern California
1150 S. Olive Street, Suite 2300
Los Angeles, CA 90115, USA
ATTN: Accounting
DISCLAIMER. USC MAKES NO EXPRESS OR IMPLIED WARRANTIES, EITHER IN FACT OR BY OPERATION OF LAW, BY STATUTE OR OTHERWISE, AND USC SPECIFICALLY AND EXPRESSLY DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, VALIDITY OF THE SOFTWARE OR ANY OTHER INTELLECTUAL PROPERTY RIGHTS OR NON-INFRINGEMENT OF THE INTELLECTUAL PROPERTY OR OTHER RIGHTS OF ANY THIRD PARTY. SOFTWARE IS MADE AVAILABLE AS-IS. LIMITATION OF LIABILITY. TO THE MAXIMUM EXTENT PERMITTED BY LAW, IN NO EVENT WILL USC BE LIABLE TO ANY USER OF THIS CODE FOR ANY INCIDENTAL, CONSEQUENTIAL, EXEMPLARY OR PUNITIVE DAMAGES OF ANY KIND, LOST GOODWILL, LOST PROFITS, LOST BUSINESS AND/OR ANY INDIRECT ECONOMIC DAMAGES WHATSOEVER, REGARDLESS OF WHETHER SUCH DAMAGES ARISE FROM CLAIMS BASED UPON CONTRACT, NEGLIGENCE, TORT (INCLUDING STRICT LIABILITY OR OTHER LEGAL THEORY), A BREACH OF ANY WARRANTY OR TERM OF THIS AGREEMENT, AND REGARDLESS OF WHETHER USC WAS ADVISED OR HAD REASON TO KNOW OF THE POSSIBILITY OF INCURRING SUCH DAMAGES IN ADVANCE.
For commercial license pricing and annual commercial update and support pricing, please contact:
Rakesh Pandit USC Stevens Institute for Innovation
University of Southern California
1150 S. Olive Street, Suite 2300
Los Angeles, CA 90115, USA
Tel: +1 213-821-3552
Fax: +1 213-821-5001
Email: rakeshvp@usc.edu and ccto: accounting@stevens.usc.edu