Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING

Abstract: 

Fake news and deep fakes have been making social and mainstream media headlines. At the same time, engaged scientists strive for find- ing ways to detect forgeries and suspicious manipulations using even the subtlest clues. In this vein, this work proposes a new method for detecting photographic splicing by bringing together the high repre- sentation power of Illuminant Maps and Convolutional Neural Net- works as a way of learning directly from available training data the most important hints of a forgery. This work propose a method that eliminates the laborious feature engineering process, allow locate forgery region and yields a classification accuracy of more than 96%, outperforming state-of-the-art methods in different datasets. The po- tential uses of the proposed method is further highlighted by analyz- ing some suspicious real-world photographs that recently broke the news

up
0 users have voted:

Paper Details

Authors:
Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho
Submitted On:
7 October 2018 - 5:48am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Tiago Carvalho
Paper Code:
2085
Document Year:
2018
Cite

Document Files

ICIP-Poster-V2.pdf

(82)

Subscribe

[1] Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho, "IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3588. Accessed: May. 20, 2019.
@article{3588-18,
url = {http://sigport.org/3588},
author = {Thales Pomari; Guillherme Ruppert; Edmar Rezende; Anderson Rocha; Tiago Carvalho },
publisher = {IEEE SigPort},
title = {IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING},
year = {2018} }
TY - EJOUR
T1 - IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING
AU - Thales Pomari; Guillherme Ruppert; Edmar Rezende; Anderson Rocha; Tiago Carvalho
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3588
ER -
Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho. (2018). IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING. IEEE SigPort. http://sigport.org/3588
Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho, 2018. IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING. Available at: http://sigport.org/3588.
Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho. (2018). "IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING." Web.
1. Thales Pomari, Guillherme Ruppert, Edmar Rezende, Anderson Rocha, Tiago Carvalho. IMAGE SPLICING DETECTION THROUGH ILLUMINATION INCONSISTENCIES AND DEEP LEARNING [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3588