Shadow Removal Detection and Localization for Forensics Analysis
Sri Kalyan Yarlagadda, David Güera, Daniel Mas Montserrat, Fengqing Maggie Zhu, Edward J. Delp, Paolo Bestagini, Stefano Tubaro
Abstract
The recent advancements in image processing and computer vision allow realistic photo manipulations. In order to avoid the distribution of fake imagery, the image forensics community is working towards the development of image authenticity verification tools. Methods based on shadow analysis are particularly reliable since they are part of the physical integrity of the scene, thus detecting forgeries is possible whenever inconsistencies are found (e.g., shadows not coherent with the light direction). An attacker can easily delete inconsistent shadows and replace them with correctly cast shadows in order to fool forensics detectors based on physical analysis. In this paper, we propose a method to detect shadow removal done with state-of-the-art tools. The proposed method is based on a conditional generative adversarial network (cGAN) specifically trained for shadow removal detection.
BibTeX
@inproceedings{icassp2019_shadowremovaldet,
title = {Shadow Removal Detection and Localization for Forensics Analysis},
author = {Sri Kalyan Yarlagadda and David Güera and Daniel Mas Montserrat and Fengqing Maggie Zhu and Edward J. Delp and Paolo Bestagini and Stefano Tubaro},
booktitle = {ICASSP 2019},
year = {2019}
}